Describe your changes here

.cursor/rules/olv-core-rules.mdc

@@ -0,0 +1,111 @@
+---
+alwaysApply: true
+---
+
+
+# Open-LLM-VTuber AI Coding Assistant: Context & Guidelines
+
+`version: 2025.08.05-1`
+
+## 1. Core Project Context
+
+  - **Project:** Open-LLM-VTuber, a low-latency voice-based LLM interaction tool.
+  - **Language:** Python >= 3.10
+  - **Core Tech Stack:**
+      - **Backend:** FastAPI, Pydantic v2, Uvicorn, fully async
+      - **Real-time Communication:** WebSockets
+      - **Package Management:** `uv` (version ~= 0.8, as of 2025 August) (always use `uv run`, `uv sync`, `uv add`, `uv remove` to do stuff instead of `pip`)
+  - **Primary Goal:** Achieve end-to-end latency below 500ms (user speaks -> AI voice heard). Performance is critical.
+  - **Key Principles:**
+      - **Offline-Ready:** Core functionality MUST work without an internet connection.
+      - **Separation of Concerns:** Strict frontend-backend separation.
+      - **Clean code:** Clean, testable, maintainable code, follows best practices of python 3.10+ and does not write deprecated code.
+
+Some key files and directories:
+
+```
+doc/                 # A deprecated directory
+frontend/            # Compiled web frontend artifacts (from git submodule)
+config_templates/
+    conf.default.yaml    # Configuration template for English users
+    conf.ZH.default.yaml # Configuration template for Chinese users
+src/open_llm_vtuber/ # Project source code
+    config_manager/
+        main.py      # Pydantic models for configuration validation
+run_server.py        # Entrypoint to start the application
+conf.yaml            # User's configuration file, generated from a template
+```
+
+### 1.1. Repository Structure
+
+- Frontend Repository: The frontend is a React application developed in a separate repository: `Open-LLM-VTuber-Web`. Its built artifacts are integrated into the `frontend/` directory of this backend repository via a git submodule.
+
+- Documentation Repository: The official documentation site is hosted in the `open-llm-vtuber.github.io` repository. When asked to generate documentation, create Markdown files in the project root. The user will be responsible for migrating them to the documentation site.
+
+### 1.2. Configuration Files
+
+- Configuration templates are located in the `config_templates/` directory:
+- `conf.default.yaml`: Template for English-speaking users.
+- `conf.ZH.default.yaml`: Template for Chinese-speaking users.
+- When modifying the configuration structure, both template files MUST be updated accordingly.
+- Configuration is validated on load using the Pydantic models defined in `src/open_llm_vtuber/config_manager/main.py`. Any changes to configuration options must be reflected in these models.
+
+## 2. Overarching Coding Philosophy
+
+  - **Simplicity and Readability:** Write code that is simple, clear, and easy to understand. Avoid unnecessary complexity or premature optimization. Follow the Zen of Python.
+  - **Single Responsibility:** Each function, class, and module should do one thing and do it well.
+  - **Performance-Aware:** Be mindful of performance. Avoid blocking operations in async contexts. Use efficient data structures and algorithms where it matters.
+  - **Adherence to Best Practices**: Write clean, testable, and robust code that follows modern Python 3.10+ idioms. Adhere to the best practices of our core libraries (FastAPI, Pydantic v2).
+
+## 3. Detailed Coding Standards
+
+### 3.1. Formatting & Linting (Ruff)
+
+  - All Python code **MUST** be formatted with `uv run ruff format`.
+  - All Python code **MUST** pass `uv run ruff check` without errors.
+  - Import statements should be grouped by standard library, third-party, and local modules and sorted alphabetically (PEP 8).
+
+### 3.2. Naming Conventions (PEP 8)
+
+  - Use `snake_case` for all variables, functions, methods, and module names.
+  - Use `PascalCase` for class names.
+  - Choose descriptive names. Avoid single-letter names except for loop counters or well-known initialisms.
+
+### 3.3. Type Hints (CRITICAL)
+
+  - Target Python 3.10+. Use modern type hint syntax.
+  - **DO:** Use `|` for unions (e.g., `str | None`).
+  - **DON'T:** Use `Optional` from `typing` (e.g., `Optional[str]`).
+  - **DO:** Use built-in generics (e.g., `list[int]`, `dict[str, float]`).
+  - **DON'T:** Use capitalized types from `typing` (e.g., `List[int]`, `Dict[str, float]`).
+  - All function and method signatures (arguments and return values) **MUST** have accurate type hints. If third party libraries made it impossible to fix type errors, suppress the type checker.
+
+### 3.4. Docstrings & Comments (CRITICAL)
+
+  - All public modules, functions, classes, and methods **MUST** have a docstring in English.
+  - Use the **Google Python Style** for docstrings.
+  - Docstrings **MUST** include:
+    1.  Summary.
+    2.  `Args:` section describing each parameter, its type, and its purpose.
+    3.  `Returns:` section describing the return value, its type, and its meaning.
+    4.  (Optional but encouraged) `Raises:` section for any exceptions thrown.
+  - All other code comments must also be in English.
+
+### 3.5. Logging
+
+  - Use the `loguru` module for all informational or error output.
+  - Log messages should be in English, clear, and informative. Use emoji when appropriate.
+
+## 4. Architectural Principles
+
+### 4.1. Dependency Management
+
+  - First, try to solve the problem using the Python standard library or existing project dependencies defined in `pyproject.toml`.
+  - If a new dependency is required, it must have a compatible license and be well-maintained.
+  - Use `uv add`, `uv remove`, `uv run` instead of pip to manage dependencies. If user uses conda, install uv with pip then.
+  - After adding a new dependency, in addition to `pyproject.toml`, you must add the dependency to `requirements.txt` as well.
+
+### 4.2. Cross-Platform Compatibility
+
+  - All core logic **MUST** run on macOS, Windows, and Linux.
+  - If a feature is platform-specific (e.g., uses a Windows-only API) or hardware-specific (e.g., CUDA), it **MUST** be an optional component. The application should start and run core features even if that component is not available. Use graceful fallbacks or clear error messages.

.dockerignore

@@ -0,0 +1,79 @@
+# User config & backup
+/conf.yaml
+# Avatars
+# avatars/*
+# Backgrounds
+# backgrounds/*
+
+/conf.yaml.backup
+
+# Default templates retained
+!/config_templates/**
+
+# Live2D models - ignore non-defaults
+live2d-models/*
+!live2d-models/mao_pro/**
+!live2d-models/shizuku/**
+
+# Characters
+characters/*
+# All default characters tracked via git
+
+
+
+# System files
+.DS_Store
+
+# Python cache
+__pycache__/
+*.pyc
+
+# IDE & local files
+/.idea/
+lab.py
+
+# Virtual envs
+.venv/
+.conda/
+conda/
+
+# API keys, secrets
+.env
+api_keys.py
+src/open_llm_vtuber/llm/user_credentials.json
+
+# Database
+memory.db*
+mem.json
+
+# Logs
+server.log
+logs/*
+
+# Cache & models
+cache/*
+asset/
+models/*
+!models/piper_voice/**
+src/open_llm_vtuber/tts/asset/
+src/open_llm_vtuber/tts/config/
+src/open_llm_vtuber/asr/models/*
+!src/open_llm_vtuber/asr/models/silero_vad.onnx
+
+# Misc
+tmp/
+private/
+legacy/
+chat_history/
+knowledge_base/
+submodules/MeloTTS
+openapi_*.json
+
+# Windows builds
+*.exe
+
+# Packaging artifacts
+*.egg-info/
+build/
+dist/
+.cache/

.gemini/GEMINI.md

@@ -0,0 +1,106 @@
+# Open-LLM-VTuber AI Coding Assistant: Context & Guidelines
+
+`version: 2025.08.05-1`
+
+## 1. Core Project Context
+
+  - **Project:** Open-LLM-VTuber, a low-latency voice-based LLM interaction tool.
+  - **Language:** Python >= 3.10
+  - **Core Tech Stack:**
+      - **Backend:** FastAPI, Pydantic v2, Uvicorn, fully async
+      - **Real-time Communication:** WebSockets
+      - **Package Management:** `uv` (version ~= 0.8, as of 2025 August) (always use `uv run`, `uv sync`, `uv add`, `uv remove` to do stuff instead of `pip`)
+  - **Primary Goal:** Achieve end-to-end latency below 500ms (user speaks -> AI voice heard). Performance is critical.
+  - **Key Principles:**
+      - **Offline-Ready:** Core functionality MUST work without an internet connection.
+      - **Separation of Concerns:** Strict frontend-backend separation.
+      - **Clean code:** Clean, testable, maintainable code, follows best practices of python 3.10+ and does not write deprecated code.
+
+Some key files and directories:
+
+```
+doc/                 # A deprecated directory
+frontend/            # Compiled web frontend artifacts (from git submodule)
+config_templates/
+    conf.default.yaml    # Configuration template for English users
+    conf.ZH.default.yaml # Configuration template for Chinese users
+src/open_llm_vtuber/ # Project source code
+    config_manager/
+        main.py      # Pydantic models for configuration validation
+run_server.py        # Entrypoint to start the application
+conf.yaml            # User's configuration file, generated from a template
+```
+
+### 1.1. Repository Structure
+
+- Frontend Repository: The frontend is a React application developed in a separate repository: `Open-LLM-VTuber-Web`. Its built artifacts are integrated into the `frontend/` directory of this backend repository via a git submodule.
+
+- Documentation Repository: The official documentation site is hosted in the `open-llm-vtuber.github.io` repository. When asked to generate documentation, create Markdown files in the project root. The user will be responsible for migrating them to the documentation site.
+
+### 1.2. Configuration Files
+
+- Configuration templates are located in the `config_templates/` directory:
+- `conf.default.yaml`: Template for English-speaking users.
+- `conf.ZH.default.yaml`: Template for Chinese-speaking users.
+- When modifying the configuration structure, both template files MUST be updated accordingly.
+- Configuration is validated on load using the Pydantic models defined in `src/open_llm_vtuber/config_manager/main.py`. Any changes to configuration options must be reflected in these models.
+
+## 2. Overarching Coding Philosophy
+
+  - **Simplicity and Readability:** Write code that is simple, clear, and easy to understand. Avoid unnecessary complexity or premature optimization. Follow the Zen of Python.
+  - **Single Responsibility:** Each function, class, and module should do one thing and do it well.
+  - **Performance-Aware:** Be mindful of performance. Avoid blocking operations in async contexts. Use efficient data structures and algorithms where it matters.
+  - **Adherence to Best Practices**: Write clean, testable, and robust code that follows modern Python 3.10+ idioms. Adhere to the best practices of our core libraries (FastAPI, Pydantic v2).
+
+## 3. Detailed Coding Standards
+
+### 3.1. Formatting & Linting (Ruff)
+
+  - All Python code **MUST** be formatted with `uv run ruff format`.
+  - All Python code **MUST** pass `uv run ruff check` without errors.
+  - Import statements should be grouped by standard library, third-party, and local modules and sorted alphabetically (PEP 8).
+
+### 3.2. Naming Conventions (PEP 8)
+
+  - Use `snake_case` for all variables, functions, methods, and module names.
+  - Use `PascalCase` for class names.
+  - Choose descriptive names. Avoid single-letter names except for loop counters or well-known initialisms.
+
+### 3.3. Type Hints (CRITICAL)
+
+  - Target Python 3.10+. Use modern type hint syntax.
+  - **DO:** Use `|` for unions (e.g., `str | None`).
+  - **DON'T:** Use `Optional` from `typing` (e.g., `Optional[str]`).
+  - **DO:** Use built-in generics (e.g., `list[int]`, `dict[str, float]`).
+  - **DON'T:** Use capitalized types from `typing` (e.g., `List[int]`, `Dict[str, float]`).
+  - All function and method signatures (arguments and return values) **MUST** have accurate type hints. If third party libraries made it impossible to fix type errors, suppress the type checker.
+
+### 3.4. Docstrings & Comments (CRITICAL)
+
+  - All public modules, functions, classes, and methods **MUST** have a docstring in English.
+  - Use the **Google Python Style** for docstrings.
+  - Docstrings **MUST** include:
+    1.  Summary.
+    2.  `Args:` section describing each parameter, its type, and its purpose.
+    3.  `Returns:` section describing the return value, its type, and its meaning.
+    4.  (Optional but encouraged) `Raises:` section for any exceptions thrown.
+  - All other code comments must also be in English.
+
+### 3.5. Logging
+
+  - Use the `loguru` module for all informational or error output.
+  - Log messages should be in English, clear, and informative. Use emoji when appropriate.
+
+## 4. Architectural Principles
+
+### 4.1. Dependency Management
+
+  - First, try to solve the problem using the Python standard library or existing project dependencies defined in `pyproject.toml`.
+  - If a new dependency is required, it must have a compatible license and be well-maintained.
+  - Use `uv add`, `uv remove`, `uv run` instead of pip to manage dependencies. If user uses conda, install uv with pip then.
+  - After adding a new dependency, in addition to `pyproject.toml`, you must add the dependency to `requirements.txt` as well.
+
+### 4.2. Cross-Platform Compatibility
+
+  - All core logic **MUST** run on macOS, Windows, and Linux.
+  - If a feature is platform-specific (e.g., uses a Windows-only API) or hardware-specific (e.g., CUDA), it **MUST** be an optional component. The application should start and run core features even if that component is not available. Use graceful fallbacks or clear error messages.

.gemini/styleguide.md

@@ -0,0 +1,165 @@
+version: 2025.08.04-1-en
+
+# Pull Request Guide & Checklist
+
+Welcome, and thank you for choosing to contribute to the Open-LLM-VTuber project! We are deeply grateful for the effort of every contributor.
+
+This guide is designed to help all contributors, maintainers, and even LLMs collaborate effectively, ensuring the project's high quality, maintainability, and long-term health. Please refer to this guide both when submitting a Pull Request (PR) and when reviewing PRs from others.
+
+We believe that clear standards and processes are not only the cornerstone of project maintenance but also an excellent opportunity for us to learn and grow together.
+
+⚠️ The coding standards mentioned below apply primarily to new code submissions. Some legacy code may not currently pass all type checks. We are working to fix this incrementally, but it will take time. When encountering type errors reported by the type checker, please focus only on the parts of the code your PR modifies. Adhere to principle **A1 (A PR should do one thing)**. If you wish to help fix existing type errors, please open a separate PR for that purpose.
+
+---
+
+### A. The Golden Rule: Atomic PRs
+
+This is our most important principle. Please adhere to it strictly.
+
+**A1. A single PR should do one thing, and one thing only.**
+
+* **Good examples 👍:**
+    * `fix: Resolve audio stuttering on macOS`
+    * `feat: Add OpenAI TTS support`
+    * `refactor: Rework the audio_processing module`
+* **Bad examples 👎:**
+    * `fix: Resolve bug A, bug B, and implement feature C`
+
+**Why is this so important?**
+
+* **Easy to Review:** Small, focused PRs allow reviewers to understand your changes more quickly and deeply, leading to higher-quality feedback. As stated in *The Pragmatic Programmer*, "Tip 38: It's Easier to Change Sooner." Small PRs facilitate rapid feedback loops.
+* **Easy to Track:** When a problem arises in the future, a clean Git history (thanks to `git bisect`) allows us to quickly pinpoint the exact change that introduced the issue.
+* **Easy to Revert:** If a small change introduces a bug, we can easily revert it without impacting other unrelated features or fixes.
+
+### B. Contributor's Checklist: Submitting My PR
+
+Before you submit your PR, please confirm each of the following items. This not only significantly speeds up the merge process but is also a sign of respect for your own work and for your fellow collaborators.
+
+#### B1. PR Title & Description
+
+* [ ] **B1.1: Clear Title:** The title should concisely summarize the core content of the PR. For example: `feat: Add OpenAI TTS support` or `fix: Resolve audio stuttering on macOS`. Remember, a PR should only do one thing (A1).
+* [ ] **B1.2: Complete Description:** The description area should clearly explain:
+    * **What:** Briefly describe the purpose and context of this PR.
+    * **Why:** Explain the necessity of this change. If it's a bug fix, please link to the relevant Issue.
+    * **How:** Briefly outline the technical implementation approach.
+    * **How to Test:** Provide clear, step-by-step instructions so that reviewers can reproduce and verify your work.
+
+#### B2. Code Quality Self-Check
+
+* [ ] **B2.1: Atomicity:** Does my PR strictly adhere to the **A1** principle?
+* [ ] **B2.2: Formatting & Linting:** Have I run and passed the following commands locally?
+    ```bash
+    uv run ruff format
+    uv run ruff check
+    ```
+* [ ] **B2.3: Naming Conventions:** Do all variable, function, and module names follow **D3.2**? (i.e., PEP 8's `snake_case` style).
+* [ ] **B2.4: Type Hints & Docstrings:**
+    * [ ] **B2.4.1:** Do all new or modified functions include Type Hints compliant with **D3.3**?
+    * [ ] **B2.4.2:** Do all new or modified functions include English Docstrings compliant with **D3.3**?
+* [ ] **B2.5: Dependency Management:** If I've added a new third-party library, have I carefully considered and followed the principles in **D5. Dependency Management**?
+* [ ] **B2.6: Cross-Platform Compatibility:** Does my code run correctly on macOS, Windows, and Linux? If I've introduced components specific to a platform or GPU, have I made them optional?
+* [ ] **B2.7: Comment Language:** Are all in-code comments, Docstrings, and console outputs in English? (This excludes i18n localization implementations, but English must be the default).
+
+#### B3. Functional & Logical Self-Check
+
+* [ ] **B3.1: Functional Testing:** Have I thoroughly tested my changes locally to ensure they work as expected and do not introduce new bugs?
+* [ ] **B3.2: Alignment with Project Goals:** Do my changes align with the **D1. Core Project Goals** and not conflict with the **D2. Future Project Goals**?
+
+#### B4. Documentation Update
+
+* [ ] **B4.1: Documentation Sync:** If my PR introduces a new feature, a new configuration option, or any change that users need to be aware of, have I updated the relevant documentation in the docs repository (https://github.com/Open-LLM-VTuber/open-llm-vtuber.github.io)? (No exceptions).
+* [ ] **B4.2: Changelog Entry:** (Optional, but recommended) Add a brief entry for your change under the "Unreleased" section in `CHANGELOG.md`.
+
+### C. Maintainer's Checklist: Reviewing a PR
+
+For the long-term health of the project, please carefully check the following items during a code review. You can reference these item numbers directly (e.g., "Regarding C2.1, I believe the maintenance cost of this feature might outweigh its benefits...") to initiate a discussion.
+
+* [ ] **C1. Understand the Change:** Have I fully read and understood all the code and the intent behind this PR?
+* [ ] **C2. Strategic Alignment:**
+    * [ ] **C2.1: Necessity vs. Maintenance Cost:** Is this feature truly necessary? Does the value it provides justify the future maintenance cost we will incur? As Fred Brooks wrote in *The Mythical Man-Month*, "the conceptual integrity of the product... is the most important consideration in system design."
+    * [ ] **C2.2: Core Goal Alignment:** Does it fully align with the **D1. Core Project Goals**?
+    * [ ] **C2.3: Future Goal Alignment:** Is it consistent with, or at least not in conflict with, the **D2. Future Project Goals** and the project roadmap?
+* [ ] **C3. Implementation Quality:**
+    * [ ] **C3.1: Design Elegance:** Is the implementation sufficiently "simple" and "elegant"? Is there any over-engineering or premature optimization? "Simplicity is the ultimate sophistication." - Leonardo da Vinci.
+    * [ ] **C3.2: Maintainability:** Is the code modular, loosely coupled, easy to understand, and testable?
+    * [ ] **C3.3: Technical Detail Check:** Have all items from the contributor's self-checklist (**B2, B3, B4**) been met? (e.g., Are Type Hints accurate? Are Docstrings clear? Do Ruff checks pass?).
+* [ ] **C4. Documentation Completeness:** Has the relevant documentation been created or updated, and is its content clear and accurate?
+
+### D. Project Reference Standards
+
+This section details our core values and technical specifications, which serve as the basis for all the checklists above.
+
+#### D1. Core Project Goals
+
+* **D1.1. Offline Operation:** The project's core functionality must support fully offline operation. Any feature requiring an internet connection must be an optional module.
+* **D1.2. Frontend-Backend Separation:** Strictly adhere to a separated frontend-backend architecture to facilitate independent development and maintenance.
+* **D1.3. Cross-Platform:** Core backend components must run on macOS, Windows, and Linux via CPU. Any component dependent on a specific platform or GPU must be optional.
+* **D1.4. Updatability:** Users should be able to upgrade smoothly via an update script. Any Breaking Changes must be accompanied by a major version bump (e.g., v1 -> v2) and a switch to a new release branch.
+* **D1.5. Maintainability:** The code must be simple, modular, decoupled, testable, and follow best practices.
+
+#### D2. Future Project Goals
+
+We are moving in the following directions. All new contributions should strive to align with these goals (though it's not strictly mandatory, as these goals will likely be implemented together in a future v2 refactor).
+
+* **D2.1. GUI for Settings:** Gradually replace traditional `yaml` configuration files with a GUI-based settings interface.
+* **D2.2. Plugin Architecture:** Build a plugin-based ecosystem, using a Launcher service to manage and run modules like ASR/TTS/LLM via a GUI.
+* **D2.3. Stable API:** Provide a stable and reliable backend API for plugins and the frontend to consume.
+* **D2.4. Automated Testing:** Comprehensively adopt `pytest`-based automated testing. New code should be designed with testability in mind.
+
+#### D3. Detailed Coding Standards
+
+**D3.1. Linter & Formatter**
+We use **Ruff** to unify code style and check for potential issues. All submitted code must pass both `ruff format` and `ruff check`.
+
+**D3.2. Naming Conventions**
+* Follow Python's **PEP 8** style guide.
+* Use **snake_case** for naming variables, functions, and modules.
+* Names should be clear, descriptive, and unambiguous. Avoid single-letter variable names (except for loop counters).
+
+**D3.3. Type Hints & Docstrings**
+* **Why are they important?** Type Hints and Docstrings are the "manual" for your code. They help:
+    * Other developers to quickly understand your code.
+    * IDEs and static analysis tools (like VSCode, Ruff) to perform smarter error checking and code completion.
+    * You, months from now, to understand the code you wrote yourself.
+* **Type Hint Requirements:**
+    * All function/method parameters and return values **must** include Type Hints.
+    * The project targets **Python 3.10+**. Please use modern syntax, such as `str | None` instead of `Optional[str]`, and `list[str]` instead of `List[str]` (as per [PEP 604](https://peps.python.org/pep-0604/) and [PEP 585](https://peps.python.org/pep-0585/)).
+    * Type Hints must be accurate. It is recommended to set VSCode's Python type checker to `basic` or `strict` mode for validation.
+* **Docstring Requirements:**
+    * All new or significantly modified public functions, methods, and classes **must** include an English Docstring.
+    * We recommend the **Google style Docstring format**. It should include at least:
+        * **Summary:** A one-line summary of the function's purpose.
+        * **Args:** A description of each parameter's type and meaning.
+        * **Returns:** A description of the return value's type and meaning.
+    * **Example:**
+        ```python
+        def add(a: int, b: int) -> int:
+            """Calculates the sum of two integers.
+
+            Args:
+                a: The first integer.
+                b: The second integer.
+
+            Returns:
+                The sum of a and b.
+            """
+            return a + b
+        ```
+
+#### D4. Architectural Principles
+
+* **D4.1. ASR/LLM/TTS Module Design:** When a library supports multiple models with vastly different configurations, prioritize user experience and ease of understanding.
+    * It is recommended to encapsulate each complex model into a separate, independent module (e.g., `asr-whisper-api`, `asr-funasr`) rather than treating the entire library as one monolithic module. This simplifies user configuration and clarifies responsibilities.
+
+#### D5. Dependency Management Principles
+
+* **D5.1. Every new dependency must be carefully considered.**
+    * Can this functionality be achieved with the standard library or an existing dependency?
+    * Is the dependency's license compatible with our project?
+    * Is the dependency's community active? How is its maintenance status? Is it secure and trustworthy? Does it pose a risk of supply chain attacks?
+
+---
+
+Thank you for taking the time to read this guide. We look forward to your contribution!
+
+Finally, regarding the PR review process, please be patient. Our project is understaffed, and the core maintainers are also quite busy, so reviews may take some time. If a week passes without any response, I apologize in advance—I may have simply forgotten. Please feel free to ping me (@t41372) or other relevant maintainers in the Pull Request to remind us.

.gitattributes

@@ -1,35 +1 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+static/libs/* linguist-vendored

.github/FUNDING.yml

@@ -0,0 +1,14 @@
+# These are supported funding model platforms
+
+github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
+polar: # Replace with a single Polar username
+buy_me_a_coffee: yi.ting
+custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.github/ISSUE_TEMPLATE/bug---question---get-help---bug---提问---求助.md

@@ -0,0 +1,79 @@
+---
+name: Bug & Question & Get Help | Bug & 提问 & 求助
+about: Describe this issue template's purpose here. 请描述你遇到的问题
+title: "[GET HELP] "
+labels: question
+assignees: ''
+
+---
+
+### 1. Checklist / 检查项
+
+- [ ]  I have removed sensitive information from configuration/logs.
+    
+    我已移除配置或日志中的敏感信息。
+    
+- [ ]  I have checked the [FAQ](https://docs.llmvtuber.com/docs/faq/) and [existing issues](https://github.com/Open-LLM-VTuber/Open-LLM-VTuber/issues).
+    
+    我已查阅[常见问题](https://docs.llmvtuber.com/docs/faq/)和[已有 issue](https://github.com/Open-LLM-VTuber/Open-LLM-VTuber/issues)。
+    
+- [ ]  I am using the latest version of the project.
+    
+    我正在使用项目的最新版本。
+    
+
+---
+
+### 2. Environment Details / 环境信息
+
+- How did you install Open-LLM-VTuber:
+    
+    你是如何安装 Open-LLM-VTuber 的：
+    
+    - [ ]  git clone （源码克隆）
+    - [ ]  release zip （发布包）
+    - [ ]  exe (Windows) （Windows 安装包）
+    - [ ]  dmg (MacOS) （MacOS 安装包）
+- Are you running the backend and frontend on the same device?
+    
+    后端和前端是否在同一台设备上运行？
+    
+- If you used GPU, please provide your GPU model and driver version:
+    
+    如果你使用了 GPU，请提供你的 GPU 型号及驱动版本信息:
+    
+- Browser (if applicable):
+
+       浏览器（如果适用）：
+
+---
+
+### 3. Describe the bug / 问题描述
+
+What exactly is happening? What do you want to see? How to reproduce?
+
+请详细描述发生了什么、你希望看到什么，以及如何复现。
+
+---
+
+### 4. Screenshots / Logs (if relevant)
+
+截图 / 日志（如有）
+
+- Backend log: 后端日志
+- Frontend setting (General): 前端设置（通用）
+- Frontend console log (F12): 前端控制台日志（F12）
+- If using Ollama: output of `ollama ps`:
+如果使用 Ollama，请附上 `ollama ps` 的输出
+
+---
+
+### 5. Configuration / 配置文件
+
+> Please provide relevant config files, with sensitive info like API keys removed
+> 
+> 
+> 请提供相关配置文件（请务必去除 API key 等敏感信息）
+> 
+- `conf.yaml`
+- `model_dict.json`, `.model3.json`

.github/ISSUE_TEMPLATE/feature-request---功能建议.md

@@ -0,0 +1,44 @@
+---
+name: Feature request / 功能建议
+about: Suggest an idea for this project / 提出改善项目的建议
+title: "[IDEA]"
+labels: enhancement
+assignees: ''
+
+---
+
+### 这个功能请求是用来解决什么问题的？ / Is your feature request related to a problem? Please describe.
+*请清晰简洁地描述您遇到的问题。例如：我总是在 [...] 时感到不方便。*
+*A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] *
+
+[在这里输入问题描述 / Type problem description here]
+
+### 您期望的解决方案是什么？ / Describe the solution you'd like
+*请清晰简洁地描述您希望实现的功能或效果。*
+*A clear and concise description of what you want to happen.*
+
+[在此处输入期望的解决方案 / Type desired solution here]
+
+### 此功能为何对 Open-LLM-VTuber 很重要？ / Why is this important for Open-LLM-VTuber?
+*请解释为什么这个功能对 Open-LLM-VTuber 项目来说是实用且重要的。它能带来什么价值？例如，它如何提升用户体验、扩展项目能力、解决核心痛点等。*
+*Explain why this feature would be useful and significant for the Open-LLM-VTuber project. What value does it add? For example, how does it improve user experience, extend project capabilities, or solve core pain points?*
+
+[在此处说明其重要性 / Explain its importance here]
+
+### 您考虑过哪些替代方案？ / Describe alternatives you've considered
+*请清晰简洁地描述您考虑过的任何替代解决方案或特性。*
+*A clear and concise description of any alternative solutions or features you've considered.*
+
+[在此处输入替代方案 / Type alternatives here]
+
+### 您是否愿意参与开发此功能？ / Would you like to work on this issue?
+*请回答 Yes 或 No。如果您愿意，我们可以讨论后续步骤。*
+*Please answer Yes or No. If yes, we can discuss the next steps.*
+
+[回答 Yes/No / Answer Yes/No]
+
+### 补充信息 / Additional context
+*在此处添加有关此功能请求的任何其他上下文、截图、日志或设计稿。*
+*Add any other context, screenshots, logs, or mockups about the feature request here.*
+
+[在此处添加补充信息 / Add additional context here]

.github/copilot-instructions.md

@@ -0,0 +1,106 @@
+# Open-LLM-VTuber AI Coding Assistant: Context & Guidelines
+
+`version: 2025.08.05-1`
+
+## 1. Core Project Context
+
+  - **Project:** Open-LLM-VTuber, a low-latency voice-based LLM interaction tool.
+  - **Language:** Python >= 3.10
+  - **Core Tech Stack:**
+      - **Backend:** FastAPI, Pydantic v2, Uvicorn, fully async
+      - **Real-time Communication:** WebSockets
+      - **Package Management:** `uv` (version ~= 0.8, as of 2025 August) (always use `uv run`, `uv sync`, `uv add`, `uv remove` to do stuff instead of `pip`)
+  - **Primary Goal:** Achieve end-to-end latency below 500ms (user speaks -> AI voice heard). Performance is critical.
+  - **Key Principles:**
+      - **Offline-Ready:** Core functionality MUST work without an internet connection.
+      - **Separation of Concerns:** Strict frontend-backend separation.
+      - **Clean code:** Clean, testable, maintainable code, follows best practices of python 3.10+ and does not write deprecated code.
+
+Some key files and directories:
+
+```
+doc/                 # A deprecated directory
+frontend/            # Compiled web frontend artifacts (from git submodule)
+config_templates/
+    conf.default.yaml    # Configuration template for English users
+    conf.ZH.default.yaml # Configuration template for Chinese users
+src/open_llm_vtuber/ # Project source code
+    config_manager/
+        main.py      # Pydantic models for configuration validation
+run_server.py        # Entrypoint to start the application
+conf.yaml            # User's configuration file, generated from a template
+```
+
+### 1.1. Repository Structure
+
+- Frontend Repository: The frontend is a React application developed in a separate repository: `Open-LLM-VTuber-Web`. Its built artifacts are integrated into the `frontend/` directory of this backend repository via a git submodule.
+
+- Documentation Repository: The official documentation site is hosted in the `open-llm-vtuber.github.io` repository. When asked to generate documentation, create Markdown files in the project root. The user will be responsible for migrating them to the documentation site.
+
+### 1.2. Configuration Files
+
+- Configuration templates are located in the `config_templates/` directory:
+- `conf.default.yaml`: Template for English-speaking users.
+- `conf.ZH.default.yaml`: Template for Chinese-speaking users.
+- When modifying the configuration structure, both template files MUST be updated accordingly.
+- Configuration is validated on load using the Pydantic models defined in `src/open_llm_vtuber/config_manager/main.py`. Any changes to configuration options must be reflected in these models.
+
+## 2. Overarching Coding Philosophy
+
+  - **Simplicity and Readability:** Write code that is simple, clear, and easy to understand. Avoid unnecessary complexity or premature optimization. Follow the Zen of Python.
+  - **Single Responsibility:** Each function, class, and module should do one thing and do it well.
+  - **Performance-Aware:** Be mindful of performance. Avoid blocking operations in async contexts. Use efficient data structures and algorithms where it matters.
+  - **Adherence to Best Practices**: Write clean, testable, and robust code that follows modern Python 3.10+ idioms. Adhere to the best practices of our core libraries (FastAPI, Pydantic v2).
+
+## 3. Detailed Coding Standards
+
+### 3.1. Formatting & Linting (Ruff)
+
+  - All Python code **MUST** be formatted with `uv run ruff format`.
+  - All Python code **MUST** pass `uv run ruff check` without errors.
+  - Import statements should be grouped by standard library, third-party, and local modules and sorted alphabetically (PEP 8).
+
+### 3.2. Naming Conventions (PEP 8)
+
+  - Use `snake_case` for all variables, functions, methods, and module names.
+  - Use `PascalCase` for class names.
+  - Choose descriptive names. Avoid single-letter names except for loop counters or well-known initialisms.
+
+### 3.3. Type Hints (CRITICAL)
+
+  - Target Python 3.10+. Use modern type hint syntax.
+  - **DO:** Use `|` for unions (e.g., `str | None`).
+  - **DON'T:** Use `Optional` from `typing` (e.g., `Optional[str]`).
+  - **DO:** Use built-in generics (e.g., `list[int]`, `dict[str, float]`).
+  - **DON'T:** Use capitalized types from `typing` (e.g., `List[int]`, `Dict[str, float]`).
+  - All function and method signatures (arguments and return values) **MUST** have accurate type hints. If third party libraries made it impossible to fix type errors, suppress the type checker.
+
+### 3.4. Docstrings & Comments (CRITICAL)
+
+  - All public modules, functions, classes, and methods **MUST** have a docstring in English.
+  - Use the **Google Python Style** for docstrings.
+  - Docstrings **MUST** include:
+    1.  Summary.
+    2.  `Args:` section describing each parameter, its type, and its purpose.
+    3.  `Returns:` section describing the return value, its type, and its meaning.
+    4.  (Optional but encouraged) `Raises:` section for any exceptions thrown.
+  - All other code comments must also be in English.
+
+### 3.5. Logging
+
+  - Use the `loguru` module for all informational or error output.
+  - Log messages should be in English, clear, and informative. Use emoji when appropriate.
+
+## 4. Architectural Principles
+
+### 4.1. Dependency Management
+
+  - First, try to solve the problem using the Python standard library or existing project dependencies defined in `pyproject.toml`.
+  - If a new dependency is required, it must have a compatible license and be well-maintained.
+  - Use `uv add`, `uv remove`, `uv run` instead of pip to manage dependencies. If user uses conda, install uv with pip then.
+  - After adding a new dependency, in addition to `pyproject.toml`, you must add the dependency to `requirements.txt` as well.
+
+### 4.2. Cross-Platform Compatibility
+
+  - All core logic **MUST** run on macOS, Windows, and Linux.
+  - If a feature is platform-specific (e.g., uses a Windows-only API) or hardware-specific (e.g., CUDA), it **MUST** be an optional component. The application should start and run core features even if that component is not available. Use graceful fallbacks or clear error messages.

.github/workflows/codeql.yml

@@ -0,0 +1,92 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL Advanced"
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+  schedule:
+    - cron: '32 5 * * 6'
+
+jobs:
+  analyze:
+    name: Analyze (${{ matrix.language }})
+    # Runner size impacts CodeQL analysis time. To learn more, please see:
+    #   - https://gh.io/recommended-hardware-resources-for-running-codeql
+    #   - https://gh.io/supported-runners-and-hardware-resources
+    #   - https://gh.io/using-larger-runners (GitHub.com only)
+    # Consider using larger runners or machines with greater resources for possible analysis time improvements.
+    runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
+    permissions:
+      # required for all workflows
+      security-events: write
+
+      # required to fetch internal or private CodeQL packs
+      packages: read
+
+      # only required for workflows in private repositories
+      actions: read
+      contents: read
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+        - language: python
+          build-mode: none
+        # CodeQL supports the following values keywords for 'language': 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'swift'
+        # Use `c-cpp` to analyze code written in C, C++ or both
+        # Use 'java-kotlin' to analyze code written in Java, Kotlin or both
+        # Use 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both
+        # To learn more about changing the languages that are analyzed or customizing the build mode for your analysis,
+        # see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/customizing-your-advanced-setup-for-code-scanning.
+        # If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how
+        # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v3
+      with:
+        languages: ${{ matrix.language }}
+        build-mode: ${{ matrix.build-mode }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+
+        # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+        # queries: security-extended,security-and-quality
+
+    # If the analyze step fails for one of the languages you are analyzing with
+    # "We were unable to automatically build your code", modify the matrix above
+    # to set the build mode to "manual" for that language. Then modify this step
+    # to build your code.
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+    - if: matrix.build-mode == 'manual'
+      shell: bash
+      run: |
+        echo 'If you are using a "manual" build mode for one or more of the' \
+          'languages you are analyzing, replace this with the commands to build' \
+          'your code, for example:'
+        echo '  make bootstrap'
+        echo '  make release'
+        exit 1
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v3
+      with:
+        category: "/language:${{matrix.language}}"

.github/workflows/create_release.yml

@@ -0,0 +1,238 @@
+name: Create Release Packages
+
+# Only manual trigger
+on:
+  workflow_dispatch:
+    inputs:
+      version_override:
+        description: "Override version number in pyproject.toml (leave empty to use file version)"
+        required: false
+      upload_to_r2:
+        description: "Upload to Cloudflare R2"
+        type: boolean
+        default: true
+      create_github_release:
+        description: "Create GitHub Release"
+        type: boolean
+        default: true
+      target_branch:
+        description: "Branch to build (default is v1-release)"
+        required: false
+        default: "v1-release"
+
+jobs:
+  build-release-packages:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clone repository
+        uses: actions/checkout@v3
+        with:
+          repository: Open-LLM-VTuber/Open-LLM-VTuber
+          ref: ${{ github.event.inputs.target_branch }}
+          submodules: true
+          fetch-depth: 1
+          fetch-tags: true
+        continue-on-error: true
+        id: checkout
+
+      - name: Try with default branch
+        if: steps.checkout.outcome == 'failure'
+        uses: actions/checkout@v3
+        with:
+          repository: Open-LLM-VTuber/Open-LLM-VTuber
+          ref: v1-release
+          submodules: true
+          fetch-depth: 1
+
+      # Add debug step to check file structure
+      - name: Debug - Check repository structure
+        run: |
+          echo "Current working directory: $(pwd)"
+          echo "List root directory contents:"
+          ls -la
+          echo "Check if config_templates directory exists:"
+          ls -la | grep config_templates || echo "config_templates directory does not exist"
+
+          echo "List config_templates directory contents:"
+          ls -la config_templates/
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+
+      - name: Extract version from pyproject.toml
+        id: get_version
+        run: |
+          VERSION=$(grep -m 1 'version' pyproject.toml | sed 's/[^"]*"\([^"]*\).*/\1/')
+          if [ "${{ github.event.inputs.version_override }}" != "" ]; then
+            VERSION="${{ github.event.inputs.version_override }}"
+          fi
+          echo "VERSION=$VERSION" >> $GITHUB_ENV
+          echo "Found version: $VERSION"
+
+      # Download and prepare ASR model
+      - name: Download and prepare ASR model
+        run: |
+          mkdir -p models
+          cd models
+          echo "Downloading ASR model..."
+          wget https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2
+          echo "Extracting model..."
+          tar -xjf sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2
+          rm sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17.tar.bz2
+          echo "Removing model.onnx file to reduce size..."
+          rm -f sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/model.onnx
+
+      # Clean unnecessary files
+      - name: Clean project
+        run: |
+          echo "Cleaning __pycache__ and .venv folders..."
+          find . -type d -name "__pycache__" -exec rm -rf {} + 2>/dev/null || true
+          find . -type d -name ".venv" -exec rm -rf {} + 2>/dev/null || true
+
+      # Create Chinese version
+      - name: Create Chinese version
+        run: |
+          echo "Creating Chinese version..."
+          cp config_templates/conf.ZH.default.yaml conf.yaml
+          zip -r Open-LLM-VTuber-v${{ env.VERSION }}-zh.zip . -x "*.zip"
+          rm conf.yaml
+
+      # Create English version
+      - name: Create English version
+        run: |
+          echo "Creating English version..."
+          cp config_templates/conf.default.yaml conf.yaml
+          zip -r Open-LLM-VTuber-v${{ env.VERSION }}-en.zip . -x "*.zip"
+          rm conf.yaml
+
+      # Get latest Electron app
+      - name: Get latest Electron app
+        id: download_electron
+        run: |
+          set -e
+
+          # Fetch the latest release JSON from the GitHub API
+          RELEASE_JSON=$(curl --silent "https://api.github.com/repos/Open-LLM-VTuber/Open-LLM-VTuber-Web/releases/latest")
+
+          # Use jq to extract browser_download_url for assets ending with .exe or .dmg
+          ASSET_URLS=$(echo "$RELEASE_JSON" | jq -r '.assets[] | select(.name | endswith(".exe") or endswith(".dmg")) | .browser_download_url')
+
+          # Download each asset into the current directory
+          for url in $ASSET_URLS; do
+              echo "Downloading $(basename "$url")..."
+              curl -L -O "$url"
+          ls -la
+          done
+
+      # If chosen, upload to GitHub Actions artifacts
+      - name: Upload Chinese version to GitHub Actions artifacts
+        if: ${{ github.event.inputs.create_github_release == 'true' }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: Open-LLM-VTuber-v${{ env.VERSION }}-zh
+          path: Open-LLM-VTuber-v${{ env.VERSION }}-zh.zip
+          retention-days: 30
+
+      - name: Upload English version to GitHub Actions artifacts
+        if: ${{ github.event.inputs.create_github_release == 'true' }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: Open-LLM-VTuber-v${{ env.VERSION }}-en
+          path: Open-LLM-VTuber-v${{ env.VERSION }}-en.zip
+          retention-days: 30
+
+      - name: Upload Windows installer to GitHub Actions artifacts
+        if: ${{ github.event.inputs.create_github_release == 'true' }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: Open-LLM-VTuber-v${{ env.VERSION }}-windows
+          path: open-llm-vtuber-electron-*-setup.exe
+          retention-days: 30
+
+      - name: Upload macOS installer to GitHub Actions artifacts
+        if: ${{ github.event.inputs.create_github_release == 'true' }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: Open-LLM-VTuber-v${{ env.VERSION }}-macos
+          path: open-llm-vtuber-electron-*.dmg
+          retention-days: 30
+
+      - name: Debug input parameters
+        run: |
+          echo "upload_to_r2 value: '${{ github.event.inputs.upload_to_r2 }}'"
+          echo "type: $(typeof ${{ github.event.inputs.upload_to_r2 }})"
+          
+      # If chosen, upload to Cloudflare R2
+      - name: Upload to Cloudflare R2
+        if: ${{ github.event.inputs.upload_to_r2 == 'true' }}
+        env:
+          AWS_ACCESS_KEY_ID: ${{ secrets.R2_ACCESS_KEY_ID }}
+          AWS_SECRET_ACCESS_KEY: ${{ secrets.R2_SECRET_ACCESS_KEY }}
+          R2_ENDPOINT: ${{ secrets.R2_ENDPOINT }}
+          R2_PUBLIC_URL: ${{ secrets.R2_PUBLIC_URL }}
+        run: |
+          # Install AWS CLI
+          pip install awscli
+          echo "AWS CLI installation complete"
+          # Configure AWS CLI for Cloudflare R2
+          aws configure set aws_access_key_id "$AWS_ACCESS_KEY_ID"
+          aws configure set aws_secret_access_key "$AWS_SECRET_ACCESS_KEY"
+
+          # Confirm AWS CLI configuration
+          echo "AWS CLI configured, preparing to upload files..."
+
+          # Create version directory in bucket
+          aws s3 --endpoint-url=$R2_ENDPOINT cp --recursive --acl public-read . s3://open-llm-vtuber-release/v${{ env.VERSION }}/ --exclude "*" --include "Open-LLM-VTuber-v${{ env.VERSION }}-*.zip" --include "open-llm-vtuber-electron-*.dmg" --include "open-llm-vtuber-electron-*-setup.exe"
+
+          # Output public URLs
+          echo "Files uploaded to R2. Public URLs:"
+          for file in Open-LLM-VTuber-v${{ env.VERSION }}-zh.zip Open-LLM-VTuber-v${{ env.VERSION }}-en.zip open-llm-vtuber-electron-*.dmg open-llm-vtuber-electron-*-setup.exe; do
+            echo "$R2_PUBLIC_URL/v${{ env.VERSION }}/$file"
+          done   
+
+          echo "R2 upload process completed"
+          
+      # Generate download links markdown
+      - name: Generate R2 download links markdown
+        if: ${{ github.event.inputs.upload_to_r2 == 'true' }}
+        env:
+          R2_PUBLIC_URL: ${{ secrets.R2_PUBLIC_URL }}
+        run: |
+          # Get electron app version from filenames
+          EXE_VERSION=$(ls open-llm-vtuber-electron-*-setup.exe | sed -E 's/open-llm-vtuber-electron-(.*)-setup.exe/\1/')
+          DMG_VERSION=$(ls open-llm-vtuber-electron-*.dmg | sed -E 's/open-llm-vtuber-electron-(.*).dmg/\1/')
+          
+          # Create markdown text with download links and save to file
+          cat > download-links.md << EOF
+          
+          ## Faster download links for Chinese users 给内地用户准备的(相对)快速的下载链接
+          Open-LLM-VTuber-v${{ env.VERSION }}-zh.zip (包含 sherpa onnx asr 的 sense-voice 模型，就不用再从github上拉取了)
+          - [Open-LLM-VTuber-v${{ env.VERSION }}-en.zip]($R2_PUBLIC_URL/v${{ env.VERSION }}/Open-LLM-VTuber-v${{ env.VERSION }}-en.zip)
+          - [Open-LLM-VTuber-v${{ env.VERSION }}-zh.zip]($R2_PUBLIC_URL/v${{ env.VERSION }}/Open-LLM-VTuber-v${{ env.VERSION }}-zh.zip)
+          
+          open-llm-vtuber-electron-$EXE_VERSION-frontend.exe (桌面版前端，Windows)
+          - [open-llm-vtuber-electron-$EXE_VERSION-setup.exe]($R2_PUBLIC_URL/v${{ env.VERSION }}/open-llm-vtuber-electron-$EXE_VERSION-setup.exe)
+          
+          open-llm-vtuber-electron-$DMG_VERSION-frontend.dmg (桌面版前端，macOS)
+          - [open-llm-vtuber-electron-$DMG_VERSION.dmg]($R2_PUBLIC_URL/v${{ env.VERSION }}/open-llm-vtuber-electron-$DMG_VERSION.dmg)
+          EOF
+          
+          echo "Download links markdown file created"
+      
+      # Upload download links as an artifact
+      - name: Upload download links markdown
+        if: ${{ github.event.inputs.upload_to_r2 == 'true' }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: download-links
+          path: download-links.md
+          retention-days: 30
+          
+      # Add the download links to GitHub release if creating one
+      - name: Add download links to release description
+        if: ${{ github.event.inputs.upload_to_r2 == 'true' && github.event.inputs.create_github_release == 'true' }}
+        run: |
+          echo "::set-output name=download_links::$(cat download-links.md)"
+        id: download_links

.github/workflows/docker-blacksmith.yml

@@ -0,0 +1,207 @@
+name: Docker Build & Push (Blacksmith)
+
+on:
+  push:
+    branches:
+      - main
+    tags:
+      - "v*"
+      - "*.*.*"
+  pull_request:
+    branches:
+      - main
+  workflow_dispatch:
+
+concurrency:
+  group: docker-blacksmith-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+  packages: write
+
+env:
+  DOCKERFILE: dockerfile
+  CONTEXT: .
+  DOCKERHUB_IMAGE: ${{ vars.DOCKERHUB_IMAGE || 'openllmvtuber/open-llm-vtuber' }}
+  GHCR_IMAGE: ${{ vars.GHCR_IMAGE || '' }}
+
+jobs:
+  meta:
+    runs-on: blacksmith-8vcpu-ubuntu-2204
+    outputs:
+      tags: ${{ steps.meta.outputs.tags }}
+      labels: ${{ steps.meta.outputs.labels }}
+      dockerhub_image: ${{ steps.image.outputs.dockerhub_image }}
+      ghcr_image: ${{ steps.image.outputs.ghcr_image }}
+    steps:
+      - name: Resolve image names
+        id: image
+        shell: bash
+        run: |
+          set -euo pipefail
+          dockerhub_image="${DOCKERHUB_IMAGE}"
+          if [ -n "${GHCR_IMAGE:-}" ]; then
+            ghcr_image="${GHCR_IMAGE}"
+          else
+            ghcr_image="ghcr.io/${GITHUB_REPOSITORY,,}"
+          fi
+          echo "dockerhub_image=${dockerhub_image}" >> "$GITHUB_OUTPUT"
+          echo "ghcr_image=${ghcr_image}" >> "$GITHUB_OUTPUT"
+
+      - name: Docker image metadata
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            ${{ steps.image.outputs.dockerhub_image }}
+            ${{ steps.image.outputs.ghcr_image }}
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=sha,format=short
+            type=raw,value=latest,enable={{is_default_branch}}
+
+  build:
+    needs: meta
+    runs-on: ${{ matrix.runner }}
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - platform: amd64
+            runner: blacksmith-8vcpu-ubuntu-2204
+            docker_platform: linux/amd64
+          - platform: arm64
+            runner: blacksmith-8vcpu-ubuntu-2204-arm
+            docker_platform: linux/arm64
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Blacksmith Docker builder
+        uses: useblacksmith/setup-docker-builder@v1
+
+      - name: Login to Docker Hub (retry)
+        if: github.event_name != 'pull_request'
+        shell: bash
+        env:
+          DOCKERHUB_USERNAME: ${{ secrets.DOCKERHUB_USERNAME }}
+          DOCKERHUB_TOKEN: ${{ secrets.DOCKERHUB_TOKEN }}
+        run: |
+          set -euo pipefail
+          for attempt in 1 2 3 4; do
+            if echo "${DOCKERHUB_TOKEN}" | docker login -u "${DOCKERHUB_USERNAME}" --password-stdin; then
+              exit 0
+            fi
+            if [ "${attempt}" -eq 4 ]; then
+              echo "Docker Hub login failed after ${attempt} attempts." >&2
+              exit 1
+            fi
+            sleep $((attempt * 5))
+          done
+
+      - name: Login to GHCR (retry)
+        if: github.event_name != 'pull_request'
+        shell: bash
+        env:
+          GHCR_USER: ${{ github.actor }}
+          GHCR_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          set -euo pipefail
+          for attempt in 1 2 3 4; do
+            if echo "${GHCR_TOKEN}" | docker login ghcr.io -u "${GHCR_USER}" --password-stdin; then
+              exit 0
+            fi
+            if [ "${attempt}" -eq 4 ]; then
+              echo "GHCR login failed after ${attempt} attempts." >&2
+              exit 1
+            fi
+            sleep $((attempt * 5))
+          done
+
+      - name: Prepare temporary arch tags
+        id: temp-tags
+        shell: bash
+        run: |
+          set -euo pipefail
+          ref_slug="$(echo "${GITHUB_REF_NAME}" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9_.-]/-/g')"
+          suffix="tmp-${ref_slug}-${{ matrix.platform }}"
+          {
+            echo "tags<<EOF"
+            echo "${{ needs.meta.outputs.dockerhub_image }}:${suffix}"
+            echo "${{ needs.meta.outputs.ghcr_image }}:${suffix}"
+            echo "EOF"
+          } >> "$GITHUB_OUTPUT"
+
+      - name: Build and push (${{ matrix.platform }})
+        uses: useblacksmith/build-push-action@v2
+        with:
+          context: ${{ env.CONTEXT }}
+          file: ${{ env.DOCKERFILE }}
+          platforms: ${{ matrix.docker_platform }}
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.temp-tags.outputs.tags }}
+          labels: ${{ needs.meta.outputs.labels }}
+
+  manifest:
+    needs: [meta, build]
+    runs-on: ubuntu-latest
+    if: github.event_name != 'pull_request'
+    steps:
+      - name: Login to Docker Hub (retry)
+        shell: bash
+        env:
+          DOCKERHUB_USERNAME: ${{ secrets.DOCKERHUB_USERNAME }}
+          DOCKERHUB_TOKEN: ${{ secrets.DOCKERHUB_TOKEN }}
+        run: |
+          set -euo pipefail
+          for attempt in 1 2 3 4; do
+            if echo "${DOCKERHUB_TOKEN}" | docker login -u "${DOCKERHUB_USERNAME}" --password-stdin; then
+              exit 0
+            fi
+            if [ "${attempt}" -eq 4 ]; then
+              echo "Docker Hub login failed after ${attempt} attempts." >&2
+              exit 1
+            fi
+            sleep $((attempt * 5))
+          done
+
+      - name: Login to GHCR (retry)
+        shell: bash
+        env:
+          GHCR_USER: ${{ github.actor }}
+          GHCR_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          set -euo pipefail
+          for attempt in 1 2 3 4; do
+            if echo "${GHCR_TOKEN}" | docker login ghcr.io -u "${GHCR_USER}" --password-stdin; then
+              exit 0
+            fi
+            if [ "${attempt}" -eq 4 ]; then
+              echo "GHCR login failed after ${attempt} attempts." >&2
+              exit 1
+            fi
+            sleep $((attempt * 5))
+          done
+
+      - name: Set up Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Create and push multi-arch manifests
+        shell: bash
+        run: |
+          set -euo pipefail
+          ref_slug="$(echo "${GITHUB_REF_NAME}" | tr '[:upper:]' '[:lower:]' | sed 's/[^a-z0-9_.-]/-/g')"
+          suffix_base="tmp-${ref_slug}"
+          mapfile -t tags <<< "${{ needs.meta.outputs.tags }}"
+          for tag in "${tags[@]}"; do
+            [ -z "$tag" ] && continue
+            base="${tag%:*}"
+            docker buildx imagetools create \
+              --tag "$tag" \
+              "${base}:${suffix_base}-amd64" \
+              "${base}:${suffix_base}-arm64"
+          done

.github/workflows/fossa_scan.yml

@@ -0,0 +1,16 @@
+name: Fossa Scan
+
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  fossa-scan:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: fossas/fossa-action@main
+        with:
+          api-key: ${{ secrets.fossaApiKey }}

.github/workflows/ruff.yml

@@ -0,0 +1,8 @@
+name: Ruff
+on: [ push, pull_request ]
+jobs:
+  ruff:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/ruff-action@v3

.github/workflows/update-requirements.yml

@@ -0,0 +1,30 @@
+name: Sync Requirements
+
+on:
+  push:
+    paths:
+      - pyproject.toml
+
+jobs:
+  regenerate:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v3
+      - name: Compile default requirements
+        run: uv pip compile pyproject.toml -o requirements.txt --no-deps --universal
+      - name: Compile bilibili requirements
+        run: uv pip compile pyproject.toml --extra bilibili -o requirements-bilibili.txt --no-deps --universal --no-annotate --no-header
+      - name: Commit updated requirements
+        uses: stefanzweifel/git-auto-commit-action@v5
+        with:
+          commit_message: "chore: update requirements files (bot)"
+          file_pattern: |
+            requirements.txt
+            requirements-bilibili.txt

.gitignore

@@ -0,0 +1,78 @@
+# ignore the user configuration file
+conf.yaml
+
+# ignore non-default background images
+/backgrounds/*
+!/backgrounds/README.md
+
+# ignore non-default live2d models
+/live2d-models/*
+!/live2d-models/mao_pro
+!/live2d-models/shizuku
+
+# ignore non-default character configs
+/characters/*
+!/characters/README.md
+# but all of the defaults are already tracked, so no need to un-ignore them
+
+# ignore avatars
+avatars/*
+
+# macOS system files
+.DS_Store
+
+# Python files
+__pycache__/
+*.pyc
+lab.py
+.idea
+
+# Virtual environment
+.venv
+.conda
+conda
+
+# Sensitive data
+.env
+api_keys.py
+src/open_llm_vtuber/llm/user_credentials.json
+
+# Database files
+memory.db
+memory.db.bk
+
+# Logs
+server.log
+logs/*
+
+# Cache and models
+cache/*
+src/open_llm_vtuber/tts/asset
+src/open_llm_vtuber/tts/config
+src/open_llm_vtuber/asr/models*
+!src/open_llm_vtuber/asr/models/silero_vad.onnx
+asset
+models/*
+!models/piper_voice
+models/piper_voice/*
+
+
+# Legacy and specific directories
+legacy/
+chat_history/
+knowledge_base/
+submodules/MeloTTS
+openapi_assistants.json
+openapi_memgpt.json
+
+# memory log
+mem.json
+conf.yaml.backup
+
+*.exe
+
+tmp/
+private/
+mcp_servers.json
+
+.vscode/

.gitmodules

@@ -0,0 +1,4 @@
+[submodule "frontend"]
+	path = frontend
+	url = https://github.com/Open-LLM-VTuber/Open-LLM-VTuber-Web
+	branch = build

.pre-commit-config.yaml

@@ -0,0 +1,9 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.9.6
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+      - id: ruff-format
+
+        

.python-version

@@ -0,0 +1 @@
+3.10

CLAUDE.md

@@ -0,0 +1,156 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project Overview
+
+Open-LLM-VTuber is a voice-interactive AI companion with Live2D avatar support that runs completely offline. It's a cross-platform Python application supporting real-time voice conversations, visual perception, and Live2D character animations. The project features modular architecture for LLM, ASR (Automatic Speech Recognition), TTS (Text-to-Speech), and other components.
+
+## Essential Commands
+
+### Development Setup
+- **Install dependencies**: `uv sync` (uses uv package manager)
+- **Run server**: `uv run run_server.py`
+- **Run with verbose logging**: `uv run run_server.py --verbose`
+- **Update project**: `uv run upgrade.py`
+
+### Code Quality
+- **Lint code**: `ruff check .`
+- **Format code**: `ruff format .`
+- **Run pre-commit hooks**: `pre-commit run --all-files`
+
+### Server Configuration
+- **Main config file**: `conf.yaml` (user configuration)
+- **Default configs**: `config_templates/conf.default.yaml` and `config_templates/conf.ZH.default.yaml`
+- **Character configs**: `characters/` directory (YAML files)
+
+## Architecture Overview
+
+### Core Components
+
+**WebSocket Server** (`src/open_llm_vtuber/server.py`):
+- FastAPI-based server handling WebSocket connections
+- Serves frontend, Live2D models, and static assets
+- Supports both main client and proxy WebSocket endpoints
+
+**Service Context** (`src/open_llm_vtuber/service_context.py`):
+- Central dependency injection container
+- Manages all engines (LLM, ASR, TTS, VAD, etc.)
+- Each WebSocket connection gets its own service context instance
+
+**WebSocket Handler** (`src/open_llm_vtuber/websocket_handler.py`):
+- Routes WebSocket messages to appropriate handlers
+- Manages client connections, groups, and conversation state
+- Handles audio data, conversation triggers, and Live2D interactions
+
+### Modular Engine System
+
+The project uses a factory pattern for all AI engines:
+
+**Agent System** (`src/open_llm_vtuber/agent/`):
+- `agent_factory.py` - Factory for creating different agent types
+- `agents/` - Various agent implementations (basic_memory, hume_ai, letta, mem0)
+- `stateless_llm/` - Stateless LLM implementations (Claude, OpenAI, Ollama, etc.)
+
+**ASR Engines** (`src/open_llm_vtuber/asr/`):
+- Support for multiple ASR backends: Sherpa-ONNX, FunASR, Faster-Whisper, OpenAI Whisper, etc.
+- Factory pattern for engine selection based on configuration
+
+**TTS Engines** (`src/open_llm_vtuber/tts/`):
+- Multiple TTS options: Azure TTS, Edge TTS, MeloTTS, CosyVoice, GPT-SoVITS, etc.
+- Configurable voice cloning and multi-language support
+
+**VAD (Voice Activity Detection)** (`src/open_llm_vtuber/vad/`):
+- Silero VAD for detecting speech activity
+- Essential for voice interruption without feedback loops
+
+### Configuration Management
+
+**Config System** (`src/open_llm_vtuber/config_manager/`):
+- Type-safe configuration classes for each component
+- Automatic validation and loading from YAML files
+- Support for multiple character configurations and config switching
+
+### Conversation System
+
+**Conversation Handling** (`src/open_llm_vtuber/conversations/`):
+- `conversation_handler.py` - Main conversation orchestration
+- `single_conversation.py` - Individual user conversations
+- `group_conversation.py` - Multi-user group conversations
+- `tts_manager.py` - Audio streaming and TTS management
+
+### MCP (Model Context Protocol) Integration
+
+**MCP System** (`src/open_llm_vtuber/mcpp/`):
+- Tool execution and server registry
+- JSON detection and parameter extraction
+- Integration with various MCP servers for extended functionality
+
+## Key Development Patterns
+
+### Error Handling
+The codebase uses the missing `_cleanup_failed_connection` method pattern - when implementing new WebSocket handlers, ensure proper cleanup methods are implemented.
+
+### Live2D Integration
+- Models stored in `live2d-models/` directory
+- Each model has its own `.model3.json` configuration
+- Expression and motion control through WebSocket messages
+
+### Audio Processing
+- Real-time audio streaming through WebSocket
+- Voice interruption support without headphones
+- Multi-format audio support with proper codec handling
+
+### Multi-language Support
+- Character configurations support multiple languages
+- TTS translation capabilities (speak in different language than input)
+- I18n system for UI elements
+
+## Important File Locations
+
+- **Entry point**: `run_server.py`
+- **Main server**: `src/open_llm_vtuber/server.py`
+- **WebSocket routing**: `src/open_llm_vtuber/routes.py`
+- **Configuration**: `conf.yaml` (user), `config_templates/` (defaults)
+- **Frontend**: `frontend/` (Git submodule)
+- **Live2D models**: `live2d-models/`
+- **Character definitions**: `characters/`
+- **Chat history**: `chat_history/`
+- **Cache**: `cache/` (audio files, temporary data)
+
+## Development Guidelines
+
+### Adding New Engines
+1. Create interface in appropriate directory (e.g., `asr_interface.py`)
+2. Implement concrete class following existing patterns
+3. Add to factory class (e.g., `asr_factory.py`)
+4. Update configuration classes in `config_manager/`
+5. Add configuration options to default YAML files
+
+### WebSocket Message Handling
+1. Add message type to `MessageType` enum in `websocket_handler.py`
+2. Create handler method following `_handle_*` pattern
+3. Register in `_init_message_handlers()` dictionary
+4. Ensure proper error handling and client response
+
+### Configuration Changes
+- Always update both default config templates
+- Maintain backward compatibility when possible
+- Use the upgrade system for breaking changes
+- Validate configurations in respective config manager classes
+
+## Testing and Quality Assurance
+
+The project uses:
+- **Ruff** for linting and formatting (configured in `pyproject.toml`)
+- **Pre-commit hooks** for automated quality checks
+- **GitHub Actions** for CI/CD (`.github/workflows/`)
+- Manual testing through web interface and desktop client
+
+## Package Management
+
+Uses **uv** (modern Python package manager):
+- Dependencies defined in `pyproject.toml`
+- Lock file: `uv.lock`
+- Generated requirements: `requirements.txt` (auto-generated)
+- Optional dependencies for specific features (e.g., `bilibili` extra)

CONTRIBUTING.md

@@ -0,0 +1,4 @@
+
+Please read the [Development - Overview](https://open-llm-vtuber.github.io/docs/development-guide/overview) before contributing.
+
+If the site is down (like after a thousand years), refer to the [source repo of our documentation site](https://github.com/Open-LLM-VTuber/open-llm-vtuber.github.io/blob/main/docs/development-guide/overview.md)

Dockerfile

@@ -0,0 +1,81 @@
+FROM python:3.10-slim
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
+    UV_LINK_MODE=copy \
+    CONFIG_FILE=/app/conf/conf.yaml
+
+WORKDIR /app
+
+# Base dependencies
+RUN apt-get update -o Acquire::Retries=5 \
+ && apt-get install -y --no-install-recommends \
+      ffmpeg git curl ca-certificates \
+ && rm -rf /var/lib/apt/lists/*
+
+# Install uv
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /usr/local/bin/
+
+# Install deps (cache-friendly)
+COPY pyproject.toml uv.lock ./
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen --no-dev
+
+# Copy source & install project
+COPY . /app
+RUN uv pip install --no-deps .
+
+# Startup script
+RUN printf '%s\n' \
+  '#!/usr/bin/env sh' \
+  'set -eu' \
+  '' \
+  'mkdir -p /app/conf /app/models' \
+  '' \
+  '# 1) conf.yaml (required)' \
+  'if [ -f "/app/conf/conf.yaml" ]; then' \
+  '  echo "Using user-provided conf.yaml"' \
+  '  ln -sf /app/conf/conf.yaml /app/conf.yaml' \
+  'else' \
+  '  echo "ERROR: conf.yaml is required."' \
+  '  echo "Please mount your config dir to /app/conf"' \
+  '  exit 1' \
+  'fi' \
+  '' \
+  '# 2) model_dict.json (optional)' \
+  'if [ -f "/app/conf/model_dict.json" ]; then' \
+  '  ln -sf /app/conf/model_dict.json /app/model_dict.json' \
+  'fi' \
+  '' \
+  '# 3) live2d-models' \
+  'if [ -d "/app/conf/live2d-models" ]; then' \
+  '  rm -rf /app/live2d-models && ln -s /app/conf/live2d-models /app/live2d-models' \
+  'fi' \
+  '' \
+  '# 4) characters' \
+  'if [ -d "/app/conf/characters" ]; then' \
+  '  rm -rf /app/characters && ln -s /app/conf/characters /app/characters' \
+  'fi' \
+  '' \
+  '# 5) avatars' \
+  'if [ -d "/app/conf/avatars" ]; then' \
+  '  rm -rf /app/avatars && ln -s /app/conf/avatars /app/avatars' \
+  'fi' \
+  '' \
+  '# 6) backgrounds' \
+  'if [ -d "/app/conf/backgrounds" ]; then' \
+  '  rm -rf /app/backgrounds && ln -s /app/conf/backgrounds /app/backgrounds' \
+  'fi' \
+  '' \
+  '# 7) start app' \
+  'exec uv run run_server.py' \
+  > /usr/local/bin/start-app && chmod +x /usr/local/bin/start-app
+
+# Volumes
+VOLUME ["/app/conf", "/app/models"]
+
+EXPOSE 12393
+
+CMD ["/usr/local/bin/start-app"]

README.md

@@ -1,10 +1,158 @@
----
-title: Open LLM
-emoji: 📈
-colorFrom: yellow
-colorTo: green
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+![](./assets/banner.jpg)
+
+<h1 align="center">Open-LLM-VTuber</h1>
+<h3 align="center">
+
+[![GitHub release](https://img.shields.io/github/v/release/Open-LLM-VTuber/Open-LLM-VTuber)](https://github.com/Open-LLM-VTuber/Open-LLM-VTuber/releases) 
+[![license](https://img.shields.io/github/license/Open-LLM-VTuber/Open-LLM-VTuber)](https://github.com/Open-LLM-VTuber/Open-LLM-VTuber/blob/master/LICENSE) 
+[![CodeQL](https://github.com/Open-LLM-VTuber/Open-LLM-VTuber/actions/workflows/codeql.yml/badge.svg)](https://github.com/Open-LLM-VTuber/Open-LLM-VTuber/actions/workflows/codeql.yml)
+[![Ruff](https://github.com/Open-LLM-VTuber/Open-LLM-VTuber/actions/workflows/ruff.yml/badge.svg)](https://github.com/Open-LLM-VTuber/Open-LLM-VTuber/actions/workflows/ruff.yml)
+[![Docker](https://img.shields.io/badge/Open-LLM-VTuber%2FOpen--LLM--VTuber-%25230db7ed.svg?logo=docker&logoColor=blue&labelColor=white&color=blue)](https://hub.docker.com/r/Open-LLM-VTuber/open-llm-vtuber) 
+[![QQ User Group](https://img.shields.io/badge/QQ_User_Group-792615362-white?style=flat&logo=qq&logoColor=white)](https://qm.qq.com/q/ngvNUQpuKI)
+[![Static Badge](https://img.shields.io/badge/Join%20Chat-Zulip?style=flat&logo=zulip&label=Zulip(dev-community)&color=blue&link=https%3A%2F%2Folv.zulipchat.com)](https://olv.zulipchat.com)
+
+> **📢 v2.0 Development**: We are focusing on Open-LLM-VTuber v2.0 — a complete rewrite of the codebase. v2.0 is currently in its early discussion and planning phase. We kindly ask you to refrain from opening new issues or pull requests for feature requests on v1. To participate in the v2 discussions or contribute, join our developer community on [Zulip](https://olv.zulipchat.com). Weekly meeting schedules will be announced on Zulip. We will continue fixing bugs for v1 and work through existing pull requests.
+
+[![BuyMeACoffee](https://img.shields.io/badge/Buy%20Me%20a%20Coffee-ffdd00?style=for-the-badge&logo=buy-me-a-coffee&logoColor=black)](https://www.buymeacoffee.com/yi.ting)
+[![](https://dcbadge.limes.pink/api/server/3UDA8YFDXx)](https://discord.gg/3UDA8YFDXx)
+
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/Open-LLM-VTuber/Open-LLM-VTuber)
+
+ENGLISH README | [中文 README](./README.CN.md) | [한국어 README](./README.KR.md) | [日本語 README](./README.JP.md)
+
+[Documentation](https://open-llm-vtuber.github.io/docs/quick-start) | [![Roadmap](https://img.shields.io/badge/Roadmap-GitHub_Project-yellow)](https://github.com/orgs/Open-LLM-VTuber/projects/2)
+
+<a href="https://trendshift.io/repositories/12358" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12358" alt="Open-LLM-VTuber%2FOpen-LLM-VTuber | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+
+</h3>
+
+
+> 常见问题 Common Issues doc (Written in Chinese): https://docs.qq.com/pdf/DTFZGQXdTUXhIYWRq
+>
+> User Survey: https://forms.gle/w6Y6PiHTZr1nzbtWA
+>
+> 调查问卷(中文): https://wj.qq.com/s2/16150415/f50a/
+
+
+
+> :warning: This project is in its early stages and is currently under **active development**.
+
+> :warning: If you want to run the server remotely and access it on a different machine, such as running the server on your computer and access it on your phone, you will need to configure `https`, because the microphone on the front end will only launch in a secure context (a.k.a. https or localhost). See [MDN Web Doc](https://developer.mozilla.org/en-US/docs/Web/API/MediaDevices/getUserMedia). Therefore, you should configure https with a reverse proxy to access the page on a remote machine (non-localhost).
+
+
+
+## ⭐️ What is this project?
+
+
+**Open-LLM-VTuber** is a unique **voice-interactive AI companion** that not only supports **real-time voice conversations**  and **visual perception** but also features a lively **Live2D avatar**. All functionalities can run completely offline on your computer!
+
+You can treat it as your personal AI companion — whether you want a `virtual girlfriend`, `boyfriend`, `cute pet`, or any other character, it can meet your expectations. The project fully supports `Windows`, `macOS`, and `Linux`, and offers two usage modes: web version and desktop client (with special support for **transparent background desktop pet mode**, allowing the AI companion to accompany you anywhere on your screen).
+
+Although the long-term memory feature is temporarily removed (coming back soon), thanks to the persistent storage of chat logs, you can always continue your previous unfinished conversations without losing any precious interactive moments.
+
+In terms of backend support, we have integrated a rich variety of LLM inference, text-to-speech, and speech recognition solutions. If you want to customize your AI companion, you can refer to the [Character Customization Guide](https://open-llm-vtuber.github.io/docs/user-guide/live2d) to customize your AI companion's appearance and persona.
+
+The reason it's called `Open-LLM-Vtuber` instead of `Open-LLM-Companion` or `Open-LLM-Waifu` is because the project's initial development goal was to use open-source solutions that can run offline on platforms other than Windows to recreate the closed-source AI Vtuber `neuro-sama`.
+
+### 👀 Demo
+| ![](assets/i1.jpg) | ![](assets/i2.jpg) |
+|:---:|:---:|
+| ![](assets/i3.jpg) | ![](assets/i4.jpg) |
+
+
+## ✨ Features & Highlights
+
+- 🖥️ **Cross-platform support**: Perfect compatibility with macOS, Linux, and Windows. We support NVIDIA and non-NVIDIA GPUs, with options to run on CPU or use cloud APIs for resource-intensive tasks. Some components support GPU acceleration on macOS.
+
+- 🔒 **Offline mode support**: Run completely offline using local models - no internet required. Your conversations stay on your device, ensuring privacy and security.
+
+- 💻 **Attractive and powerful web and desktop clients**: Offers both web version and desktop client usage modes, supporting rich interactive features and personalization settings. The desktop client can switch freely between window mode and desktop pet mode, allowing the AI companion to be by your side at all times.
+
+- 🎯 **Advanced interaction features**:
+  - 👁️ Visual perception, supporting camera, screen recording and screenshots, allowing your AI companion to see you and your screen
+  - 🎤 Voice interruption without headphones (AI won't hear its own voice)
+  - 🫱 Touch feedback, interact with your AI companion through clicks or drags
+  - 😊 Live2D expressions, set emotion mapping to control model expressions from the backend
+  - 🐱 Pet mode, supporting transparent background, global top-most, and mouse click-through - drag your AI companion anywhere on the screen
+  - 💭 Display AI's inner thoughts, allowing you to see AI's expressions, thoughts and actions without them being spoken
+  - 🗣️ AI proactive speaking feature
+  - 💾 Chat log persistence, switch to previous conversations anytime
+  - 🌍 TTS translation support (e.g., chat in Chinese while AI uses Japanese voice)
+
+- 🧠 **Extensive model support**:
+  - 🤖 Large Language Models (LLM): Ollama, OpenAI (and any OpenAI-compatible API), Gemini, Claude, Mistral, DeepSeek, Zhipu AI, GGUF, LM Studio, vLLM, etc.
+  - 🎙️ Automatic Speech Recognition (ASR): sherpa-onnx, FunASR, Faster-Whisper, Whisper.cpp, Whisper, Groq Whisper, Azure ASR, etc.
+  - 🔊 Text-to-Speech (TTS): sherpa-onnx, pyttsx3, MeloTTS, Coqui-TTS, GPTSoVITS, Bark, CosyVoice, Edge TTS, Fish Audio, Azure TTS, etc.
+
+- 🔧 **Highly customizable**:
+  - ⚙️ **Simple module configuration**: Switch various functional modules through simple configuration file modifications, without delving into the code
+  - 🎨 **Character customization**: Import custom Live2D models to give your AI companion a unique appearance. Shape your AI companion's persona by modifying the Prompt. Perform voice cloning to give your AI companion the voice you desire
+  - 🧩 **Flexible Agent implementation**: Inherit and implement the Agent interface to integrate any Agent architecture, such as HumeAI EVI, OpenAI Her, Mem0, etc.
+  - 🔌 **Good extensibility**: Modular design allows you to easily add your own LLM, ASR, TTS, and other module implementations, extending new features at any time
+
+
+## 👥 User Reviews
+> Thanks to the developer for open-sourcing and sharing the girlfriend for everyone to use
+> 
+> This girlfriend has been used over 100,000 times
+
+
+## 🚀 Quick Start
+
+Please refer to the [Quick Start](https://open-llm-vtuber.github.io/docs/quick-start) section in our documentation for installation.
+
+
+
+## ☝ Update
+> :warning: `v1.0.0` has breaking changes and requires re-deployment. You *may* still update via the method below, but the `conf.yaml` file is incompatible and most of the dependencies needs to be reinstalled with `uv`. For those who came from versions before `v1.0.0`, I recommend deploy this project again with the [latest deployment guide](https://open-llm-vtuber.github.io/docs/quick-start).
+
+Please use `uv run update.py` to update if you installed any versions later than `v1.0.0`.
+
+## 😢 Uninstall  
+Most files, including Python dependencies and models, are stored in the project folder.
+
+However, models downloaded via ModelScope or Hugging Face may also be in `MODELSCOPE_CACHE` or `HF_HOME`. While we aim to keep them in the project's `models` directory, it's good to double-check.  
+
+Review the installation guide for any extra tools you no longer need, such as `uv`, `ffmpeg`, or `deeplx`.  
+
+## 🤗 Want to contribute?
+Checkout the [development guide](https://docs.llmvtuber.com/docs/development-guide/overview).
+
+
+# 🎉🎉🎉 Related Projects
+
+[ylxmf2005/LLM-Live2D-Desktop-Assitant](https://github.com/ylxmf2005/LLM-Live2D-Desktop-Assitant)
+- Your Live2D desktop assistant powered by LLM! Available for both Windows and MacOS, it senses your screen, retrieves clipboard content, and responds to voice commands with a unique voice. Featuring voice wake-up, singing capabilities, and full computer control for seamless interaction with your favorite character.
+
+
+
+
+
+
+## 📜 Third-Party Licenses
+
+### Live2D Sample Models Notice
+
+This project includes Live2D sample models provided by Live2D Inc. These assets are licensed separately under the Live2D Free Material License Agreement and the Terms of Use for Live2D Cubism Sample Data. They are not covered by the MIT license of this project.
+
+This content uses sample data owned and copyrighted by Live2D Inc. The sample data are utilized in accordance with the terms and conditions set by Live2D Inc. (See [Live2D Free Material License Agreement](https://www.live2d.jp/en/terms/live2d-free-material-license-agreement/) and [Terms of Use](https://www.live2d.com/eula/live2d-sample-model-terms_en.html)).
+
+Note: For commercial use, especially by medium or large-scale enterprises, the use of these Live2D sample models may be subject to additional licensing requirements. If you plan to use this project commercially, please ensure that you have the appropriate permissions from Live2D Inc., or use versions of the project without these models.
+
+
+## Contributors
+Thanks our contributors and maintainers for making this project possible.
+
+<a href="https://github.com/Open-LLM-VTuber/Open-LLM-VTuber/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=Open-LLM-VTuber/Open-LLM-VTuber" />
+</a>
+
+
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=Open-LLM-VTuber/open-llm-vtuber&type=Date)](https://star-history.com/#Open-LLM-VTuber/open-llm-vtuber&Date)
+
+
+
+
+

doc/README.md

@@ -0,0 +1,4 @@
+For full documentation, please visit our [documentation site](https://open-llm-vtuber.github.io/) or view the [source repository](https://github.com/Open-LLM-VTuber/open-llm-vtuber.github.io).
+
+> **Note:**  
+> The `sample_conf` directory contains legacy sample configuration files for running various models with sherpa-onnx. These files are deprecated and will be removed after we extract the relevant sherpa-onnx information.

doc/sample_conf/sherpaASRTTS_sense_voice_melo.yaml

@@ -0,0 +1,78 @@
+SYSTEM_CONFIG:
+  CONF_NAME: "sherpaASRTTS_sense_voice_melo"
+  CONF_UID: "sherpaASRTTS_sense_voice_melo"
+
+#  ============== Voice Interaction Settings ==============
+
+# === Automatic Speech Recognition ===
+VOICE_INPUT_ON: True
+# Put your mic in the browser or in the terminal? (would increase latency)
+MIC_IN_BROWSER: False # Deprecated and useless now. Do not enable it. Bad things will happen.
+
+# speech to text model options: "Faster-Whisper", "WhisperCPP", "Whisper", "AzureASR", "FunASR", "GroqWhisperASR", "SherpaOnnxASR"
+ASR_MODEL: "SherpaOnnxASR"
+
+# pip install sherpa-onnx
+# documentation: https://k2-fsa.github.io/sherpa/onnx/index.html
+# ASR models download: https://github.com/k2-fsa/sherpa-onnx/releases/tag/asr-models
+SherpaOnnxASR:
+  model_type: "sense_voice" # "transducer", "paraformer", "nemo_ctc", "wenet_ctc", "whisper", "tdnn_ctc"
+  #  Choose only ONE of the following, depending on the model_type:
+  # --- For model_type: "transducer" ---
+  # encoder: ""        # Path to the encoder model (e.g., "path/to/encoder.onnx")
+  # decoder: ""        # Path to the decoder model (e.g., "path/to/decoder.onnx")
+  # joiner: ""         # Path to the joiner model (e.g., "path/to/joiner.onnx")
+  # --- For model_type: "paraformer" ---
+  # paraformer: ""     # Path to the paraformer model (e.g., "path/to/model.onnx")
+  # --- For model_type: "nemo_ctc" ---
+  # nemo_ctc: ""        # Path to the NeMo CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "wenet_ctc" ---
+  # wenet_ctc: ""       # Path to the WeNet CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "tdnn_ctc" ---
+  # tdnn_model: ""      # Path to the TDNN CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "whisper" ---
+  # whisper_encoder: "" # Path to the Whisper encoder model (e.g., "path/to/encoder.onnx")
+  # whisper_decoder: "" # Path to the Whisper decoder model (e.g., "path/to/decoder.onnx")
+  # --- For model_type: "sense_voice" ---
+  sense_voice: "/path/to/asr-models/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/model.onnx" # Path to the SenseVoice model (e.g., "path/to/model.onnx")
+  tokens: "/path/to/asr-models/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/tokens.txt" # Path to tokens.txt (required for all model types)
+  # --- Optional parameters (with defaults shown) ---
+  # hotwords_file: ""     # Path to hotwords file (if using hotwords)
+  # hotwords_score: 1.5   # Score for hotwords
+  # modeling_unit: ""     # Modeling unit for hotwords (if applicable)
+  # bpe_vocab: ""         # Path to BPE vocabulary (if applicable)
+  num_threads: 4 # Number of threads
+  # whisper_language: "" # Language for Whisper models (e.g., "en", "zh", etc. - if using Whisper)
+  # whisper_task: "transcribe"  # Task for Whisper models ("transcribe" or "translate" - if using Whisper)
+  # whisper_tail_paddings: -1   # Tail padding for Whisper models (if using Whisper)
+  # blank_penalty: 0.0    # Penalty for blank symbol
+  # decoding_method: "greedy_search"  # "greedy_search" or "modified_beam_search"
+  # debug: False # Enable debug mode
+  # sample_rate: 16000 # Sample rate (should match the model's expected sample rate)
+  # feature_dim: 80       # Feature dimension (should match the model's expected feature dimension)
+  use_itn: True # Enable ITN for SenseVoice models (should set to False if not using SenseVoice models)
+
+# ============== Text to Speech ==============
+TTS_MODEL: "SherpaOnnxTTS"
+# text to speech model options: 
+#   "AzureTTS", "pyttsx3TTS", "edgeTTS", "barkTTS", 
+#   "cosyvoiceTTS", "meloTTS", "piperTTS", "coquiTTS",
+#   "fishAPITTS", "SherpaOnnxTTS"
+
+
+# pip install sherpa-onnx
+# documentation: https://k2-fsa.github.io/sherpa/onnx/index.html
+# TTS models download: https://github.com/k2-fsa/sherpa-onnx/releases/tag/tts-models
+SherpaOnnxTTS:
+    vits_model: "/path/to/tts-models/vits-melo-tts-zh_en/model.onnx"  # Path to VITS model file
+    vits_lexicon: "/path/to/tts-models/vits-melo-tts-zh_en/lexicon.txt"  # Path to lexicon file (optional)
+    vits_tokens: "/path/to/tts-models/vits-melo-tts-zh_en/tokens.txt"  # Path to tokens file
+    vits_data_dir: "" # "/path/to/tts-models/vits-piper-en_GB-cori-high/espeak-ng-data"  # Path to espeak-ng data (optional)
+    vits_dict_dir: "/path/to/tts-models/vits-melo-tts-zh_en/dict"  # Path to Jieba dict (optional, for Chinese)
+    tts_rule_fsts: "/path/to/tts-models/vits-melo-tts-zh_en/number.fst,/path/to/tts-models/vits-melo-tts-zh_en/phone.fst,/path/to/tts-models/vits-melo-tts-zh_en/date.fst,/path/to/tts-models/vits-melo-tts-zh_en/new_heteronym.fst" # Path to rule FSTs file (optional)
+    max_num_sentences: 2  # Max sentences per batch (or -1 for all)
+    sid: 1  # Speaker ID (for multi-speaker models)
+    provider: "cpu"  # Use "cpu", "cuda" (GPU), or "coreml" (Apple)
+    num_threads: 1  # Number of computation threads
+    speed: 1.0  # Speech speed (1.0 is normal)
+    debug: false  # Enable debug mode (True/False)

doc/sample_conf/sherpaASRTTS_sense_voice_piper_en.yaml

@@ -0,0 +1,77 @@
+SYSTEM_CONFIG:
+  CONF_NAME: "sherpaASRTTS_sense_voice_piper_en"
+  CONF_UID: "sherpaASRTTS_sense_voice_piper_en"
+
+#  ============== Voice Interaction Settings ==============
+
+# === Automatic Speech Recognition ===
+VOICE_INPUT_ON: True
+# Put your mic in the browser or in the terminal? (would increase latency)
+MIC_IN_BROWSER: False # Deprecated and useless now. Do not enable it. Bad things will happen.
+
+# speech to text model options: "Faster-Whisper", "WhisperCPP", "Whisper", "AzureASR", "FunASR", "GroqWhisperASR", "SherpaOnnxASR"
+ASR_MODEL: "SherpaOnnxASR"
+
+# pip install sherpa-onnx
+# documentation: https://k2-fsa.github.io/sherpa/onnx/index.html
+# ASR models download: https://github.com/k2-fsa/sherpa-onnx/releases/tag/asr-models
+SherpaOnnxASR:
+  model_type: "sense_voice" # "transducer", "paraformer", "nemo_ctc", "wenet_ctc", "whisper", "tdnn_ctc"
+  #  Choose only ONE of the following, depending on the model_type:
+  # --- For model_type: "transducer" ---
+  # encoder: ""        # Path to the encoder model (e.g., "path/to/encoder.onnx")
+  # decoder: ""        # Path to the decoder model (e.g., "path/to/decoder.onnx")
+  # joiner: ""         # Path to the joiner model (e.g., "path/to/joiner.onnx")
+  # --- For model_type: "paraformer" ---
+  # paraformer: ""     # Path to the paraformer model (e.g., "path/to/model.onnx")
+  # --- For model_type: "nemo_ctc" ---
+  # nemo_ctc: ""        # Path to the NeMo CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "wenet_ctc" ---
+  # wenet_ctc: ""       # Path to the WeNet CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "tdnn_ctc" ---
+  # tdnn_model: ""      # Path to the TDNN CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "whisper" ---
+  # whisper_encoder: "" # Path to the Whisper encoder model (e.g., "path/to/encoder.onnx")
+  # whisper_decoder: "" # Path to the Whisper decoder model (e.g., "path/to/decoder.onnx")
+  # --- For model_type: "sense_voice" ---
+  sense_voice: "/path/to/asr-models/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/model.onnx" # Path to the SenseVoice model (e.g., "path/to/model.onnx")
+  tokens: "/path/to/asr-models/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/tokens.txt" # Path to tokens.txt (required for all model types)
+  # --- Optional parameters (with defaults shown) ---
+  # hotwords_file: ""     # Path to hotwords file (if using hotwords)
+  # hotwords_score: 1.5   # Score for hotwords
+  # modeling_unit: ""     # Modeling unit for hotwords (if applicable)
+  # bpe_vocab: ""         # Path to BPE vocabulary (if applicable)
+  num_threads: 4 # Number of threads
+  # whisper_language: "" # Language for Whisper models (e.g., "en", "zh", etc. - if using Whisper)
+  # whisper_task: "transcribe"  # Task for Whisper models ("transcribe" or "translate" - if using Whisper)
+  # whisper_tail_paddings: -1   # Tail padding for Whisper models (if using Whisper)
+  # blank_penalty: 0.0    # Penalty for blank symbol
+  # decoding_method: "greedy_search"  # "greedy_search" or "modified_beam_search"
+  # debug: False # Enable debug mode
+  # sample_rate: 16000 # Sample rate (should match the model's expected sample rate)
+  # feature_dim: 80       # Feature dimension (should match the model's expected feature dimension)
+  use_itn: True # Enable ITN for SenseVoice models (should set to False if not using SenseVoice models)
+
+# ============== Text to Speech ==============
+TTS_MODEL: "SherpaOnnxTTS"
+# text to speech model options: 
+#   "AzureTTS", "pyttsx3TTS", "edgeTTS", "barkTTS", 
+#   "cosyvoiceTTS", "meloTTS", "piperTTS", "coquiTTS",
+#   "fishAPITTS", "SherpaOnnxTTS"
+
+# pip install sherpa-onnx
+# documentation: https://k2-fsa.github.io/sherpa/onnx/index.html
+# TTS models download: https://github.com/k2-fsa/sherpa-onnx/releases/tag/tts-models
+SherpaOnnxTTS:
+    vits_model: "/path/to/tts-models/vits-piper-en_GB-cori-high/en_GB-cori-high.onnx"  # Path to VITS model file
+    vits_lexicon: ""  # Path to lexicon file (optional)
+    vits_tokens: "/path/to/tts-models/vits-piper-en_GB-cori-high/tokens.txt"  # Path to tokens file
+    vits_data_dir: "/path/to/tts-models/vits-piper-en_GB-cori-high/espeak-ng-data"  # Path to espeak-ng data (optional)
+    vits_dict_dir: ""  # Path to Jieba dict (optional, for Chinese)
+    tts_rule_fsts: ""  # Path to rule FSTs file (optional)
+    max_num_sentences: 2  # Max sentences per batch (or -1 for all)
+    sid: 0  # Speaker ID (for multi-speaker models)
+    provider: "cpu"  # Use "cpu", "cuda" (GPU), or "coreml" (Apple)
+    num_threads: 1  # Number of computation threads
+    speed: 1.0  # Speech speed (1.0 is normal)
+    debug: false  # Enable debug mode (True/False)

doc/sample_conf/sherpaASRTTS_sense_voice_vits_zh.yaml

@@ -0,0 +1,77 @@
+SYSTEM_CONFIG:
+  CONF_NAME: "sherpaASRTTS_sense_voice_vits_zh"
+  CONF_UID: "sherpaASRTTS_sense_voice_vits_zh"
+
+#  ============== Voice Interaction Settings ==============
+
+# === Automatic Speech Recognition ===
+VOICE_INPUT_ON: True
+# Put your mic in the browser or in the terminal? (would increase latency)
+MIC_IN_BROWSER: False # Deprecated and useless now. Do not enable it. Bad things will happen.
+
+# speech to text model options: "Faster-Whisper", "WhisperCPP", "Whisper", "AzureASR", "FunASR", "GroqWhisperASR", "SherpaOnnxASR"
+ASR_MODEL: "SherpaOnnxASR"
+
+# pip install sherpa-onnx
+# documentation: https://k2-fsa.github.io/sherpa/onnx/index.html
+# ASR models download: https://github.com/k2-fsa/sherpa-onnx/releases/tag/asr-models
+SherpaOnnxASR:
+  model_type: "sense_voice" # "transducer", "paraformer", "nemo_ctc", "wenet_ctc", "whisper", "tdnn_ctc"
+  #  Choose only ONE of the following, depending on the model_type:
+  # --- For model_type: "transducer" ---
+  # encoder: ""        # Path to the encoder model (e.g., "path/to/encoder.onnx")
+  # decoder: ""        # Path to the decoder model (e.g., "path/to/decoder.onnx")
+  # joiner: ""         # Path to the joiner model (e.g., "path/to/joiner.onnx")
+  # --- For model_type: "paraformer" ---
+  # paraformer: ""     # Path to the paraformer model (e.g., "path/to/model.onnx")
+  # --- For model_type: "nemo_ctc" ---
+  # nemo_ctc: ""        # Path to the NeMo CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "wenet_ctc" ---
+  # wenet_ctc: ""       # Path to the WeNet CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "tdnn_ctc" ---
+  # tdnn_model: ""      # Path to the TDNN CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "whisper" ---
+  # whisper_encoder: "" # Path to the Whisper encoder model (e.g., "path/to/encoder.onnx")
+  # whisper_decoder: "" # Path to the Whisper decoder model (e.g., "path/to/decoder.onnx")
+  # --- For model_type: "sense_voice" ---
+  sense_voice: "/path/to/asr-models/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/model.onnx" # Path to the SenseVoice model (e.g., "path/to/model.onnx")
+  tokens: "/path/to/asr-models/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/tokens.txt" # Path to tokens.txt (required for all model types)
+  # --- Optional parameters (with defaults shown) ---
+  # hotwords_file: ""     # Path to hotwords file (if using hotwords)
+  # hotwords_score: 1.5   # Score for hotwords
+  # modeling_unit: ""     # Modeling unit for hotwords (if applicable)
+  # bpe_vocab: ""         # Path to BPE vocabulary (if applicable)
+  num_threads: 4 # Number of threads
+  # whisper_language: "" # Language for Whisper models (e.g., "en", "zh", etc. - if using Whisper)
+  # whisper_task: "transcribe"  # Task for Whisper models ("transcribe" or "translate" - if using Whisper)
+  # whisper_tail_paddings: -1   # Tail padding for Whisper models (if using Whisper)
+  # blank_penalty: 0.0    # Penalty for blank symbol
+  # decoding_method: "greedy_search"  # "greedy_search" or "modified_beam_search"
+  # debug: False # Enable debug mode
+  # sample_rate: 16000 # Sample rate (should match the model's expected sample rate)
+  # feature_dim: 80       # Feature dimension (should match the model's expected feature dimension)
+  use_itn: True # Enable ITN for SenseVoice models (should set to False if not using SenseVoice models)
+
+# ============== Text to Speech ==============
+TTS_MODEL: "SherpaOnnxTTS"
+# text to speech model options: 
+#   "AzureTTS", "pyttsx3TTS", "edgeTTS", "barkTTS", 
+#   "cosyvoiceTTS", "meloTTS", "piperTTS", "coquiTTS",
+#   "fishAPITTS", "SherpaOnnxTTS"
+
+# pip install sherpa-onnx
+# documentation: https://k2-fsa.github.io/sherpa/onnx/index.html
+# TTS models download: https://github.com/k2-fsa/sherpa-onnx/releases/tag/tts-models
+SherpaOnnxTTS:
+    vits_model: "/path/to/tts-models/sherpa-onnx-vits-zh-ll/model.onnx"  # Path to VITS model file
+    vits_lexicon: "/path/to/tts-models/sherpa-onnx-vits-zh-ll/lexicon.txt"  # Path to lexicon file (optional)
+    vits_tokens: "/path/to/tts-models/sherpa-onnx-vits-zh-ll/tokens.txt"  # Path to tokens file
+    vits_data_dir: "" # "/path/to/tts-models/vits-piper-en_GB-cori-high/espeak-ng-data"  # Path to espeak-ng data (optional)
+    vits_dict_dir: "/path/to/tts-models/sherpa-onnx-vits-zh-ll/dict"  # Path to Jieba dict (optional, for Chinese)
+    tts_rule_fsts: "/path/to/tts-models/sherpa-onnx-vits-zh-ll/number.fst,/path/to/tts-models/sherpa-onnx-vits-zh-ll/phone.fst,/path/to/tts-models/sherpa-onnx-vits-zh-ll/date.fst" # Path to rule FSTs file (optional)
+    max_num_sentences: 2  # Max sentences per batch (or -1 for all)
+    sid: 0  # Speaker ID (for multi-speaker models) 0-4
+    provider: "cpu"  # Use "cpu", "cuda" (GPU), or "coreml" (Apple)
+    num_threads: 1  # Number of computation threads
+    speed: 1.0  # Speech speed (1.0 is normal)
+    debug: false  # Enable debug mode (True/False)

doc/sample_conf/sherpaASR_paraformer.yaml

@@ -0,0 +1,65 @@
+SYSTEM_CONFIG:
+  CONF_NAME: "sherpaASR_paraformer"
+  CONF_UID: "sherpaASR_paraformer"
+
+#  ============== Voice Interaction Settings ==============
+
+# === Automatic Speech Recognition ===
+VOICE_INPUT_ON: True
+# Put your mic in the browser or in the terminal? (would increase latency)
+MIC_IN_BROWSER: False # Deprecated and useless now. Do not enable it. Bad things will happen.
+
+# speech to text model options: "Faster-Whisper", "WhisperCPP", "Whisper", "AzureASR", "FunASR", "GroqWhisperASR", "SherpaOnnxASR"
+ASR_MODEL: "SherpaOnnxASR"
+
+# pip install sherpa-onnx
+# documentation: https://k2-fsa.github.io/sherpa/onnx/index.html
+# ASR models download: https://github.com/k2-fsa/sherpa-onnx/releases/tag/asr-models
+SherpaOnnxASR:
+  model_type: "paraformer" # "transducer", "paraformer", "nemo_ctc", "wenet_ctc", "whisper", "tdnn_ctc"
+  #  Choose only ONE of the following, depending on the model_type:
+  # --- For model_type: "transducer" ---
+  # encoder: ""        # Path to the encoder model (e.g., "path/to/encoder.onnx")
+  # decoder: ""        # Path to the decoder model (e.g., "path/to/decoder.onnx")
+  # joiner: ""         # Path to the joiner model (e.g., "path/to/joiner.onnx")
+  # --- For model_type: "paraformer" ---
+  paraformer: "/path/to/asr-models/sherpa-onnx-paraformer-zh-2024-03-09/model.onnx"     # Path to the paraformer model (e.g., "path/to/model.onnx")
+  # --- For model_type: "nemo_ctc" ---
+  # nemo_ctc: ""        # Path to the NeMo CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "wenet_ctc" ---
+  # wenet_ctc: ""       # Path to the WeNet CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "tdnn_ctc" ---
+  # tdnn_model: ""      # Path to the TDNN CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "whisper" ---
+  # whisper_encoder: "" # Path to the Whisper encoder model (e.g., "path/to/encoder.onnx")
+  # whisper_decoder: "" # Path to the Whisper decoder model (e.g., "path/to/decoder.onnx")
+  # --- For model_type: "sense_voice" ---
+  # sense_voice: "/path/to/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/model.onnx" # Path to the SenseVoice model (e.g., "path/to/model.onnx")
+  tokens: "/path/to/asr-models/sherpa-onnx-paraformer-zh-2024-03-09/tokens.txt" # Path to tokens.txt (required for all model types)
+  # --- Optional parameters (with defaults shown) ---
+  # hotwords_file: ""     # Path to hotwords file (if using hotwords)
+  # hotwords_score: 1.5   # Score for hotwords
+  # modeling_unit: ""     # Modeling unit for hotwords (if applicable)
+  # bpe_vocab: ""         # Path to BPE vocabulary (if applicable)
+  num_threads: 2 # Number of threads
+  # whisper_language: "" # Language for Whisper models (e.g., "en", "zh", etc. - if using Whisper)
+  # whisper_task: "transcribe"  # Task for Whisper models ("transcribe" or "translate" - if using Whisper)
+  # whisper_tail_paddings: -1   # Tail padding for Whisper models (if using Whisper)
+  # blank_penalty: 0.0    # Penalty for blank symbol
+  # decoding_method: "greedy_search"  # "greedy_search" or "modified_beam_search"
+  # debug: False # Enable debug mode
+  # sample_rate: 16000 # Sample rate (should match the model's expected sample rate)
+  # feature_dim: 80       # Feature dimension (should match the model's expected feature dimension)
+  # use_itn: True # Enable ITN for SenseVoice models (should set to False if not using SenseVoice models)
+
+  # ============== Text to Speech ==============
+TTS_MODEL: "edgeTTS"
+# text to speech model options: 
+#   "AzureTTS", "pyttsx3TTS", "edgeTTS", "barkTTS", 
+#   "cosyvoiceTTS", "meloTTS", "piperTTS", "coquiTTS",
+#   "fishAPITTS", "SherpaOnnxTTS"
+
+edgeTTS:
+  # Check out doc at https://github.com/rany2/edge-tts
+  # Use `edge-tts --list-voices` to list all available voices
+  voice: "en-US-AvaMultilingualNeural" #"zh-CN-XiaoxiaoNeural" # "ja-JP-NanamiNeural"

doc/sample_conf/sherpaASR_sense_voice.yaml

@@ -0,0 +1,67 @@
+SYSTEM_CONFIG:
+  CONF_NAME: "sherpaASR_sense_voice"
+  CONF_UID: "sherpaASR_sense_voice"
+
+#  ============== Voice Interaction Settings ==============
+
+# === Automatic Speech Recognition ===
+VOICE_INPUT_ON: True
+# Put your mic in the browser or in the terminal? (would increase latency)
+MIC_IN_BROWSER: False # Deprecated and useless now. Do not enable it. Bad things will happen.
+
+# speech to text model options: "Faster-Whisper", "WhisperCPP", "Whisper", "AzureASR", "FunASR", "GroqWhisperASR", "SherpaOnnxASR"
+ASR_MODEL: "SherpaOnnxASR"
+
+# pip install sherpa-onnx
+# documentation: https://k2-fsa.github.io/sherpa/onnx/index.html
+# ASR models download: https://github.com/k2-fsa/sherpa-onnx/releases/tag/asr-models
+SherpaOnnxASR:
+  model_type: "sense_voice" # "transducer", "paraformer", "nemo_ctc", "wenet_ctc", "whisper", "tdnn_ctc"
+  #  Choose only ONE of the following, depending on the model_type:
+  # --- For model_type: "transducer" ---
+  # encoder: ""        # Path to the encoder model (e.g., "path/to/encoder.onnx")
+  # decoder: ""        # Path to the decoder model (e.g., "path/to/decoder.onnx")
+  # joiner: ""         # Path to the joiner model (e.g., "path/to/joiner.onnx")
+  # --- For model_type: "paraformer" ---
+  # paraformer: ""     # Path to the paraformer model (e.g., "path/to/model.onnx")
+  # --- For model_type: "nemo_ctc" ---
+  # nemo_ctc: ""        # Path to the NeMo CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "wenet_ctc" ---
+  # wenet_ctc: ""       # Path to the WeNet CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "tdnn_ctc" ---
+  # tdnn_model: ""      # Path to the TDNN CTC model (e.g., "path/to/model.onnx")
+  # --- For model_type: "whisper" ---
+  # whisper_encoder: "" # Path to the Whisper encoder model (e.g., "path/to/encoder.onnx")
+  # whisper_decoder: "" # Path to the Whisper decoder model (e.g., "path/to/decoder.onnx")
+  # --- For model_type: "sense_voice" ---
+  sense_voice: "/path/to/asr-models/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/model.onnx" # Path to the SenseVoice model (e.g., "path/to/model.onnx")
+  tokens: "/path/to/asr-models/sherpa-onnx-sense-voice-zh-en-ja-ko-yue-2024-07-17/tokens.txt" # Path to tokens.txt (required for all model types)
+  # --- Optional parameters (with defaults shown) ---
+  # hotwords_file: ""     # Path to hotwords file (if using hotwords)
+  # hotwords_score: 1.5   # Score for hotwords
+  # modeling_unit: ""     # Modeling unit for hotwords (if applicable)
+  # bpe_vocab: ""         # Path to BPE vocabulary (if applicable)
+  num_threads: 2 # Number of threads
+  # whisper_language: "" # Language for Whisper models (e.g., "en", "zh", etc. - if using Whisper)
+  # whisper_task: "transcribe"  # Task for Whisper models ("transcribe" or "translate" - if using Whisper)
+  # whisper_tail_paddings: -1   # Tail padding for Whisper models (if using Whisper)
+  # blank_penalty: 0.0    # Penalty for blank symbol
+  # decoding_method: "greedy_search"  # "greedy_search" or "modified_beam_search"
+  # debug: False # Enable debug mode
+  # sample_rate: 16000 # Sample rate (should match the model's expected sample rate)
+  # feature_dim: 80       # Feature dimension (should match the model's expected feature dimension)
+  use_itn: True # Enable ITN for SenseVoice models (should set to False if not using SenseVoice models)
+
+# ============== Text to Speech ==============
+TTS_MODEL: "edgeTTS"
+# text to speech model options: 
+#   "AzureTTS", "pyttsx3TTS", "edgeTTS", "barkTTS", 
+#   "cosyvoiceTTS", "meloTTS", "piperTTS", "coquiTTS",
+#   "fishAPITTS"
+
+
+edgeTTS:
+  # Check out doc at https://github.com/rany2/edge-tts
+  # Use `edge-tts --list-voices` to list all available voices
+  voice: "en-US-AvaMultilingualNeural" #"zh-CN-XiaoxiaoNeural" # "ja-JP-NanamiNeural"
+

model_dict.json

@@ -0,0 +1,30 @@
+[
+    {
+        "name": "mao_pro",
+        "description": "",
+        "url": "/live2d-models/mao_pro/runtime/mao_pro.model3.json",
+        "kScale": 0.5,
+        "initialXshift": 0,
+        "initialYshift": 0,
+        "kXOffset": 1150,
+        "idleMotionGroupName": "Idle",
+        "emotionMap": {
+            "neutral": 0,
+            "anger": 2,
+            "disgust": 2,
+            "fear": 1,
+            "joy": 3,
+            "smirk": 3,
+            "sadness": 1,
+            "surprise": 3
+        },
+        "tapMotions": {
+            "HitAreaHead": {
+                "": 1
+            },
+            "HitAreaBody": {
+                "": 1
+            }
+        }
+    }
+]

pixi.lock

@@ -0,0 +1,1652 @@
+version: 6
+environments:
+  default:
+    channels:
+    - url: https://conda.anaconda.org/conda-forge/
+    indexes:
+    - https://pypi.org/simple
+    packages:
+      linux-64:
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/_libgcc_mutex-0.1-conda_forge.tar.bz2
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/_openmp_mutex-4.5-2_gnu.tar.bz2
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/bzip2-1.0.8-h4bc722e_7.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/ca-certificates-2025.1.31-hbcca054_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/cuda-version-11.8-h70ddcb2_3.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/cudatoolkit-11.8.0-h4ba93d1_13.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/cudnn-8.9.7.29-hbc23b4c_3.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/ld_impl_linux-64-2.43-h712a8e2_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libexpat-2.6.4-h5888daf_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libffi-3.4.2-h7f98852_5.tar.bz2
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libgcc-14.2.0-h77fa898_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libgcc-ng-14.2.0-h69a702a_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libgomp-14.2.0-h77fa898_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/liblzma-5.6.4-hb9d3cd8_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libnsl-2.0.1-hd590300_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libsqlite-3.49.0-hee588c1_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libstdcxx-14.2.0-hc0a3c3a_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libstdcxx-ng-14.2.0-h4852527_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libuuid-2.38.1-h0b41bf4_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libxcrypt-4.4.36-hd590300_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/libzlib-1.3.1-hb9d3cd8_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/ncurses-6.5-h2d0b736_3.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/openssl-3.4.0-h7b32b05_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/python-3.12.8-h9e4cc4f_1_cpython.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/readline-8.2-h8228510_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/linux-64/tk-8.6.13-noxft_h4845f30_101.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/tzdata-2025a-h78e105d_0.conda
+      - pypi: https://files.pythonhosted.org/packages/44/4c/03fb05f56551828ec67ceb3665e5dc51638042d204983a03b0a1541475b6/aiohappyeyeballs-2.4.6-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/17/e2/9f744cee0861af673dc271a3351f59ebd5415928e20080ab85be25641471/aiohttp-3.11.12-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/ec/6a/bc7e17a3e87a2985d3e8f4da4cd0f481060eb78fb08596c42be62c90a4d9/aiosignal-1.3.2-py2.py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/78/b6/6307fbef88d9b5ee7421e68d78a9f162e0da4900bc5f5793f6d3d0e34fb8/annotated_types-0.7.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/74/86/e81814e542d1eaeec84d2312bec93a99b9ef1d78d9bfae1fc5dd74abdf15/anthropic-0.45.2-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/46/eb/e7f063ad1fec6b3178a3cd82d1a3c4de82cccf283fc42746168188e1cdd5/anyio-4.8.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/fc/30/d4986a882011f9df997a55e6becd864812ccfcd821d64aac8570ee39f719/attrs-25.1.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/83/f7/9241ad7154e554730ea56271e14ad1115c278b26a81eb892eac16fabb480/azure_cognitiveservices_speech-1.42.0-py3-none-manylinux1_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/38/fc/bce832fd4fd99766c04d1ee0eead6b0ec6486fb100ae5e74c1d91292b982/certifi-2025.1.31-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/b2/d5/da47df7004cb17e4955df6a43d14b3b4ae77737dff8bf7f8f333196717bf/cffi-1.17.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/38/6f/f5fbc992a329ee4e0f288c1fe0e2ad9485ed064cac731ed2fe47dcc38cbf/chardet-5.2.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/3e/a2/513f6cbe752421f16d969e32f3583762bfd583848b763913ddab8d9bfd4f/charset_normalizer-3.4.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/7e/d4/7ebdbd03970677812aac39c869717059dbb71a4cfc033ca6e5221787892c/click-8.1.8-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/a7/06/3d6badcf13db419e25b07041d9c7b4a2c331d3f4e7134445ec5df57714cd/coloredlogs-15.0.1-py2.py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/12/b3/231ffd4ab1fc9d679809f356cebee130ac7daa00d6d6f3206dd4fd137e9e/distro-1.9.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/f8/37/00c211f1021f9b04dde72dcbee72ce66248519c3899a47b06f8940a67c08/edge_tts-7.0.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/8f/7d/2d6ce181d7a5f51dedb8c06206cbf0ec026a99bf145edd309f9e17c3282f/fastapi-0.115.8-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/0e/e2/b066e6e02d67bf5261a6d7539648c6da3365cc9eff3eb6d82009595d84d9/flatbuffers-25.1.24-py2.py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/af/f2/64b73a9bb86f5a89fb55450e97cd5c1f84a862d4ff90d9fd1a73ab0f64a5/frozenlist-1.5.0-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/b0/6c/5a53d632b44ef7655ac8d9b34432e13160917f9307c94b1467efd34e336e/groq-0.18.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/95/04/ff642e65ad6b90db43e668d70ffb6736436c7ce41fcc549f4e9472234127/h11-0.14.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/87/f5/72347bc88306acb359581ac4d52f23c0ef445b57157adedb9aee0cd689d2/httpcore-1.0.7-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/f7/d8/b644c44acc1368938317d76ac991c9bba1166311880bcc0ac297cb9d6bd7/httptools-0.6.4-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/f0/0f/310fb31e39e2d734ccaa2c0fb981ee41f7bd5056ce9bc29b2248bd569169/humanfriendly-10.0-py2.py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/76/c6/c88e154df9c4e1a2a66ccf0005a88dfb2650c1dffb6f5ce603dfbd452ce3/idna-3.10-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/17/61/beea645c0bf398ced8b199e377b61eb999d8e46e053bb285c91c3d3eaab0/jiter-0.8.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/0e/72/a3add0e4eec4eb9e2569554f7c70f4a3c27712f40e3284d483e88094cc0e/langdetect-1.0.9.tar.gz
+      - pypi: https://files.pythonhosted.org/packages/0c/29/0348de65b8cc732daa3e33e67806420b2ae89bdce2b04af740289c5c6c8c/loguru-0.7.3-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/43/e3/7d92a15f894aa0c9c4b49b8ee9ac9850d6e63b03c9c32c0367a13ae62209/mpmath-1.3.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/d3/c8/529101d7176fe7dfe1d99604e48d69c5dfdcadb4f06561f465c8ef12b4df/multidict-6.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/0f/50/de23fde84e45f5c4fda2488c759b69990fd4512387a8632860f3ac9cd225/numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/47/42/2f71f5680834688a9c81becbe5c5bb996fd33eaed5c66ae0606c3b1d6a02/onnxruntime-1.20.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/9a/b6/2e2a011b2dc27a6711376808b4cd8c922c476ea0f1420b39892117fa8563/openai-1.61.1-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/88/ef/eb23f262cca3c0c4eb7ab1933c3b1f03d021f2c48f54763065b6f0e321be/packaging-24.2-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/1c/07/ebe102777a830bca91bbb93e3479cd34c2ca5d0361b83be9dbd93104865e/propcache-0.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/a8/45/2ebbde52ad2be18d3675b6bee50e68cd73c9e0654de77d595540b5129df8/protobuf-5.29.3-cp38-abi3-manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/13/a3/a812df4e2dd5696d1f351d58b8fe16a405b234ad2886a0dab9183fb78109/pycparser-2.22-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/f4/3c/8cc1cc84deffa6e25d2d0c688ebb80635dfdbf1dbea3e30c541c8cf4d860/pydantic-2.10.6-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/8d/f0/49129b27c43396581a635d8710dae54a791b17dfc50c70164866bbf865e3/pydantic_core-2.27.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/a6/53/d78dc063216e62fc55f6b2eebb447f6a4b0a59f55c8406376f76bf959b08/pydub-0.25.1-py2.py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/48/0a/c99fb7d7e176f8b176ef19704a32e6a9c6aafdf19ef75a187f701fc15801/pysbd-0.3.4-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/6a/3e/b68c118422ec867fa7ab88444e1274aa40681c606d59ac27de5a5588f082/python_dotenv-1.0.1-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/94/df/e1584757c736c4fba09a3fb4f22fe625cc3367b06c6ece221e4b8c1e3023/pyttsx3-2.98-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/b9/2b/614b4752f2e127db5cc206abc23a8c19678e92b23c3db30fc86ab731d3bd/PyYAML-6.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/f9/9b/335f9764261e915ed497fcdeb11df5dfd6f7bf257d4a6a2a686d80da4d54/requests-2.32.3-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/04/70/e59c192a3ad476355e7f45fb3a87326f5219cc7c472e6b040c6c6595c8f0/ruff-0.9.5-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/b0/3c/0de11ca154e24a57b579fb648151d901326d3102115bc4f9a7a86526ce54/scipy-1.15.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/48/77/a3771191d4bac619df7dc06db14a7b22dd0007548b71ee54a81f80e2d219/sherpa_onnx-1.10.43-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/b7/ce/149a00dd41f10bc29e5921b496af8b574d8413afcd5e30dfa0ed46c2cc5e/six-1.17.0-py2.py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/57/5e/70bdd9579b35003a489fc850b5047beeda26328053ebadc1fb60f320f7db/soundfile-0.13.1-py2.py3-none-manylinux_2_28_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/66/b7/4a1bc231e0681ebf339337b0cd05b91dc6a0d701fa852bb812e244b7a030/srt-3.5.3.tar.gz
+      - pypi: https://files.pythonhosted.org/packages/d9/61/f2b52e107b1fc8944b33ef56bf6ac4ebbe16d91b94d2b87ce013bf63fb84/starlette-0.45.3-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/99/ff/c87e0622b1dadea79d2fb0b25ade9ed98954c9033722eb707053d310d4f3/sympy-1.13.3-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/40/44/4a5f08c96eb108af5cb50b41f76142f0afa346dfa99d5296fe7202a11854/tabulate-0.9.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/5c/51/51c3f2884d7bab89af25f678447ea7d297b53b5a3b5730a7cb2ef6069f07/tomli-2.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/d0/30/dc54f88dd4a2b5dc8a0279bdd7270e735851848b762aeb1c1184ed1f6b14/tqdm-4.67.1-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/26/9f/ad63fc0248c5379346306f8668cda6e2e2e9c95e01216d2b8ffd9ff037d0/typing_extensions-4.12.2-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/c8/19/4ec628951a74043532ca2cf5d97b7b14863931476d117c471e8e2b1eb39f/urllib3-2.3.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/61/14/33a3a1352cfa71812a3a21e8c9bfb83f60b0011f5e36f2b1399d51928209/uvicorn-0.34.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/06/a7/b4e6a19925c900be9f98bec0a75e6e8f79bb53bdeb891916609ab3958967/uvloop-0.21.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/2b/b4/9396cc61b948ef18943e7c85ecfa64cf940c88977d882da57147f62b34b1/watchfiles-1.0.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/5a/84/44687a29792a70e111c5c477230a72c4b957d88d16141199bf9acb7537a3/websocket_client-1.8.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/81/da/72f7caabd94652e6eb7e92ed2d3da818626e70b4f2b15a854ef60bf501ec/websockets-14.2-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: https://files.pythonhosted.org/packages/1a/e1/a097d5755d3ea8479a42856f51d97eeff7a3a7160593332d98f2709b3580/yarl-1.18.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+      - pypi: .
+      win-64:
+      - conda: https://conda.anaconda.org/conda-forge/win-64/bzip2-1.0.8-h2466b09_7.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/ca-certificates-2025.1.31-h56e8100_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/cuda-version-11.8-h70ddcb2_3.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/cudatoolkit-11.8.0-h09e9e62_13.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/cudnn-8.9.7.29-he6de189_3.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/libexpat-2.6.4-he0c23c2_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/libffi-3.4.2-h8ffe710_5.tar.bz2
+      - conda: https://conda.anaconda.org/conda-forge/win-64/liblzma-5.6.4-h2466b09_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/libsqlite-3.49.0-h67fdade_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/libzlib-1.3.1-h2466b09_2.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/libzlib-wapi-1.2.13-h2466b09_6.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/openssl-3.4.0-ha4e3fda_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/python-3.12.8-h3f84c4b_1_cpython.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/tk-8.6.13-h5226925_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/noarch/tzdata-2025a-h78e105d_0.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/ucrt-10.0.22621.0-h57928b3_1.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/vc-14.3-h5fd82a7_24.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/vc14_runtime-14.42.34433-h6356254_24.conda
+      - conda: https://conda.anaconda.org/conda-forge/win-64/vs2015_runtime-14.42.34433-hfef2bbc_24.conda
+      - pypi: https://files.pythonhosted.org/packages/44/4c/03fb05f56551828ec67ceb3665e5dc51638042d204983a03b0a1541475b6/aiohappyeyeballs-2.4.6-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/3d/63/5eca549d34d141bcd9de50d4e59b913f3641559460c739d5e215693cb54a/aiohttp-3.11.12-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/ec/6a/bc7e17a3e87a2985d3e8f4da4cd0f481060eb78fb08596c42be62c90a4d9/aiosignal-1.3.2-py2.py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/78/b6/6307fbef88d9b5ee7421e68d78a9f162e0da4900bc5f5793f6d3d0e34fb8/annotated_types-0.7.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/74/86/e81814e542d1eaeec84d2312bec93a99b9ef1d78d9bfae1fc5dd74abdf15/anthropic-0.45.2-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/46/eb/e7f063ad1fec6b3178a3cd82d1a3c4de82cccf283fc42746168188e1cdd5/anyio-4.8.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/fc/30/d4986a882011f9df997a55e6becd864812ccfcd821d64aac8570ee39f719/attrs-25.1.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/52/bb/ef7a29f5717cca646be6698d80e542446a6a442be897c8f67bf93551c672/azure_cognitiveservices_speech-1.42.0-py3-none-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/38/fc/bce832fd4fd99766c04d1ee0eead6b0ec6486fb100ae5e74c1d91292b982/certifi-2025.1.31-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/50/b9/db34c4755a7bd1cb2d1603ac3863f22bcecbd1ba29e5ee841a4bc510b294/cffi-1.17.1-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/38/6f/f5fbc992a329ee4e0f288c1fe0e2ad9485ed064cac731ed2fe47dcc38cbf/chardet-5.2.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/21/5b/1b390b03b1d16c7e382b561c5329f83cc06623916aab983e8ab9239c7d5c/charset_normalizer-3.4.1-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/7e/d4/7ebdbd03970677812aac39c869717059dbb71a4cfc033ca6e5221787892c/click-8.1.8-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/a7/06/3d6badcf13db419e25b07041d9c7b4a2c331d3f4e7134445ec5df57714cd/coloredlogs-15.0.1-py2.py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/4c/44/72009bb0a0d8286f6408c9cb70552350e21e9c280bfa1ef30784b30dfc0f/comtypes-1.4.10-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/12/b3/231ffd4ab1fc9d679809f356cebee130ac7daa00d6d6f3206dd4fd137e9e/distro-1.9.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/f8/37/00c211f1021f9b04dde72dcbee72ce66248519c3899a47b06f8940a67c08/edge_tts-7.0.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/8f/7d/2d6ce181d7a5f51dedb8c06206cbf0ec026a99bf145edd309f9e17c3282f/fastapi-0.115.8-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/0e/e2/b066e6e02d67bf5261a6d7539648c6da3365cc9eff3eb6d82009595d84d9/flatbuffers-25.1.24-py2.py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/b1/56/4e45136ffc6bdbfa68c29ca56ef53783ef4c2fd395f7cbf99a2624aa9aaa/frozenlist-1.5.0-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/b0/6c/5a53d632b44ef7655ac8d9b34432e13160917f9307c94b1467efd34e336e/groq-0.18.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/95/04/ff642e65ad6b90db43e668d70ffb6736436c7ce41fcc549f4e9472234127/h11-0.14.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/87/f5/72347bc88306acb359581ac4d52f23c0ef445b57157adedb9aee0cd689d2/httpcore-1.0.7-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/12/b7/5cae71a8868e555f3f67a50ee7f673ce36eac970f029c0c5e9d584352961/httptools-0.6.4-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/f0/0f/310fb31e39e2d734ccaa2c0fb981ee41f7bd5056ce9bc29b2248bd569169/humanfriendly-10.0-py2.py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/76/c6/c88e154df9c4e1a2a66ccf0005a88dfb2650c1dffb6f5ce603dfbd452ce3/idna-3.10-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/41/69/6d4bbe66b3b3b4507e47aa1dd5d075919ad242b4b1115b3f80eecd443687/jiter-0.8.2-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/0e/72/a3add0e4eec4eb9e2569554f7c70f4a3c27712f40e3284d483e88094cc0e/langdetect-1.0.9.tar.gz
+      - pypi: https://files.pythonhosted.org/packages/0c/29/0348de65b8cc732daa3e33e67806420b2ae89bdce2b04af740289c5c6c8c/loguru-0.7.3-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/43/e3/7d92a15f894aa0c9c4b49b8ee9ac9850d6e63b03c9c32c0367a13ae62209/mpmath-1.3.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/a3/bf/f332a13486b1ed0496d624bcc7e8357bb8053823e8cd4b9a18edc1d97e73/multidict-6.1.0-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/16/2e/86f24451c2d530c88daf997cb8d6ac622c1d40d19f5a031ed68a4b73a374/numpy-1.26.4-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/dd/80/76979e0b744307d488c79e41051117634b956612cc731f1028eb17ee7294/onnxruntime-1.20.1-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/9a/b6/2e2a011b2dc27a6711376808b4cd8c922c476ea0f1420b39892117fa8563/openai-1.61.1-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/88/ef/eb23f262cca3c0c4eb7ab1933c3b1f03d021f2c48f54763065b6f0e321be/packaging-24.2-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/3b/77/a92c3ef994e47180862b9d7d11e37624fb1c00a16d61faf55115d970628b/propcache-0.2.1-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/61/fa/aae8e10512b83de633f2646506a6d835b151edf4b30d18d73afd01447253/protobuf-5.29.3-cp310-abi3-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/13/a3/a812df4e2dd5696d1f351d58b8fe16a405b234ad2886a0dab9183fb78109/pycparser-2.22-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/f4/3c/8cc1cc84deffa6e25d2d0c688ebb80635dfdbf1dbea3e30c541c8cf4d860/pydantic-2.10.6-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/1f/ea/cd7209a889163b8dcca139fe32b9687dd05249161a3edda62860430457a5/pydantic_core-2.27.2-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/a6/53/d78dc063216e62fc55f6b2eebb447f6a4b0a59f55c8406376f76bf959b08/pydub-0.25.1-py2.py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/d0/1b/2f292bbd742e369a100c91faa0483172cd91a1a422a6692055ac920946c5/pypiwin32-223-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/5a/dc/491b7661614ab97483abf2056be1deee4dc2490ecbf7bff9ab5cdbac86e1/pyreadline3-3.5.4-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/48/0a/c99fb7d7e176f8b176ef19704a32e6a9c6aafdf19ef75a187f701fc15801/pysbd-0.3.4-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/6a/3e/b68c118422ec867fa7ab88444e1274aa40681c606d59ac27de5a5588f082/python_dotenv-1.0.1-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/94/df/e1584757c736c4fba09a3fb4f22fe625cc3367b06c6ece221e4b8c1e3023/pyttsx3-2.98-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/21/27/0c8811fbc3ca188f93b5354e7c286eb91f80a53afa4e11007ef661afa746/pywin32-308-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/0c/e8/4f648c598b17c3d06e8753d7d13d57542b30d56e6c2dedf9c331ae56312e/PyYAML-6.0.2-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/f9/9b/335f9764261e915ed497fcdeb11df5dfd6f7bf257d4a6a2a686d80da4d54/requests-2.32.3-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/b7/ad/c7a900591bd152bb47fc4882a27654ea55c7973e6d5d6396298ad3fd6638/ruff-0.9.5-py3-none-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/ff/ba/31c7a8131152822b3a2cdeba76398ffb404d81d640de98287d236da90c49/scipy-1.15.1-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/32/7a/1e9a31a5d07d1d3ed53f9cca128133f52fb898cc49196fe0a66a0b056c2d/sherpa_onnx-1.10.43-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/b7/ce/149a00dd41f10bc29e5921b496af8b574d8413afcd5e30dfa0ed46c2cc5e/six-1.17.0-py2.py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/14/e9/6b761de83277f2f02ded7e7ea6f07828ec78e4b229b80e4ca55dd205b9dc/soundfile-0.13.1-py2.py3-none-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/66/b7/4a1bc231e0681ebf339337b0cd05b91dc6a0d701fa852bb812e244b7a030/srt-3.5.3.tar.gz
+      - pypi: https://files.pythonhosted.org/packages/d9/61/f2b52e107b1fc8944b33ef56bf6ac4ebbe16d91b94d2b87ce013bf63fb84/starlette-0.45.3-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/99/ff/c87e0622b1dadea79d2fb0b25ade9ed98954c9033722eb707053d310d4f3/sympy-1.13.3-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/40/44/4a5f08c96eb108af5cb50b41f76142f0afa346dfa99d5296fe7202a11854/tabulate-0.9.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/ef/60/9b9638f081c6f1261e2688bd487625cd1e660d0a85bd469e91d8db969734/tomli-2.2.1-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/d0/30/dc54f88dd4a2b5dc8a0279bdd7270e735851848b762aeb1c1184ed1f6b14/tqdm-4.67.1-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/26/9f/ad63fc0248c5379346306f8668cda6e2e2e9c95e01216d2b8ffd9ff037d0/typing_extensions-4.12.2-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/c8/19/4ec628951a74043532ca2cf5d97b7b14863931476d117c471e8e2b1eb39f/urllib3-2.3.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/61/14/33a3a1352cfa71812a3a21e8c9bfb83f60b0011f5e36f2b1399d51928209/uvicorn-0.34.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/ea/94/b0165481bff99a64b29e46e07ac2e0df9f7a957ef13bec4ceab8515f44e3/watchfiles-1.0.4-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/5a/84/44687a29792a70e111c5c477230a72c4b957d88d16141199bf9acb7537a3/websocket_client-1.8.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/b3/7d/32cdb77990b3bdc34a306e0a0f73a1275221e9a66d869f6ff833c95b56ef/websockets-14.2-cp312-cp312-win_amd64.whl
+      - pypi: https://files.pythonhosted.org/packages/e1/07/c6fe3ad3e685340704d314d765b7912993bcb8dc198f0e7a89382d37974b/win32_setctime-1.2.0-py3-none-any.whl
+      - pypi: https://files.pythonhosted.org/packages/34/45/0e055320daaabfc169b21ff6174567b2c910c45617b0d79c68d7ab349b02/yarl-1.18.3-cp312-cp312-win_amd64.whl
+      - pypi: .
+packages:
+- conda: https://conda.anaconda.org/conda-forge/linux-64/_libgcc_mutex-0.1-conda_forge.tar.bz2
+  sha256: fe51de6107f9edc7aa4f786a70f4a883943bc9d39b3bb7307c04c41410990726
+  md5: d7c89558ba9fa0495403155b64376d81
+  license: None
+  purls: []
+  size: 2562
+  timestamp: 1578324546067
+- conda: https://conda.anaconda.org/conda-forge/linux-64/_openmp_mutex-4.5-2_gnu.tar.bz2
+  build_number: 16
+  sha256: fbe2c5e56a653bebb982eda4876a9178aedfc2b545f25d0ce9c4c0b508253d22
+  md5: 73aaf86a425cc6e73fcf236a5a46396d
+  depends:
+  - _libgcc_mutex 0.1 conda_forge
+  - libgomp >=7.5.0
+  constrains:
+  - openmp_impl 9999
+  license: BSD-3-Clause
+  license_family: BSD
+  purls: []
+  size: 23621
+  timestamp: 1650670423406
+- pypi: https://files.pythonhosted.org/packages/44/4c/03fb05f56551828ec67ceb3665e5dc51638042d204983a03b0a1541475b6/aiohappyeyeballs-2.4.6-py3-none-any.whl
+  name: aiohappyeyeballs
+  version: 2.4.6
+  sha256: 147ec992cf873d74f5062644332c539fcd42956dc69453fe5204195e560517e1
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/17/e2/9f744cee0861af673dc271a3351f59ebd5415928e20080ab85be25641471/aiohttp-3.11.12-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: aiohttp
+  version: 3.11.12
+  sha256: 6dfe7f984f28a8ae94ff3a7953cd9678550dbd2a1f9bda5dd9c5ae627744c78e
+  requires_dist:
+  - aiohappyeyeballs>=2.3.0
+  - aiosignal>=1.1.2
+  - async-timeout>=4.0,<6.0 ; python_full_version < '3.11'
+  - attrs>=17.3.0
+  - frozenlist>=1.1.1
+  - multidict>=4.5,<7.0
+  - propcache>=0.2.0
+  - yarl>=1.17.0,<2.0
+  - aiodns>=3.2.0 ; (sys_platform == 'darwin' and extra == 'speedups') or (sys_platform == 'linux' and extra == 'speedups')
+  - brotli ; platform_python_implementation == 'CPython' and extra == 'speedups'
+  - brotlicffi ; platform_python_implementation != 'CPython' and extra == 'speedups'
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/3d/63/5eca549d34d141bcd9de50d4e59b913f3641559460c739d5e215693cb54a/aiohttp-3.11.12-cp312-cp312-win_amd64.whl
+  name: aiohttp
+  version: 3.11.12
+  sha256: 54775858c7f2f214476773ce785a19ee81d1294a6bedc5cc17225355aab74802
+  requires_dist:
+  - aiohappyeyeballs>=2.3.0
+  - aiosignal>=1.1.2
+  - async-timeout>=4.0,<6.0 ; python_full_version < '3.11'
+  - attrs>=17.3.0
+  - frozenlist>=1.1.1
+  - multidict>=4.5,<7.0
+  - propcache>=0.2.0
+  - yarl>=1.17.0,<2.0
+  - aiodns>=3.2.0 ; (sys_platform == 'darwin' and extra == 'speedups') or (sys_platform == 'linux' and extra == 'speedups')
+  - brotli ; platform_python_implementation == 'CPython' and extra == 'speedups'
+  - brotlicffi ; platform_python_implementation != 'CPython' and extra == 'speedups'
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/ec/6a/bc7e17a3e87a2985d3e8f4da4cd0f481060eb78fb08596c42be62c90a4d9/aiosignal-1.3.2-py2.py3-none-any.whl
+  name: aiosignal
+  version: 1.3.2
+  sha256: 45cde58e409a301715980c2b01d0c28bdde3770d8290b5eb2173759d9acb31a5
+  requires_dist:
+  - frozenlist>=1.1.0
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/78/b6/6307fbef88d9b5ee7421e68d78a9f162e0da4900bc5f5793f6d3d0e34fb8/annotated_types-0.7.0-py3-none-any.whl
+  name: annotated-types
+  version: 0.7.0
+  sha256: 1f02e8b43a8fbbc3f3e0d4f0f4bfc8131bcb4eebe8849b8e5c773f3a1c582a53
+  requires_dist:
+  - typing-extensions>=4.0.0 ; python_full_version < '3.9'
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/74/86/e81814e542d1eaeec84d2312bec93a99b9ef1d78d9bfae1fc5dd74abdf15/anthropic-0.45.2-py3-none-any.whl
+  name: anthropic
+  version: 0.45.2
+  sha256: ecd746f7274451dfcb7e1180571ead624c7e1195d1d46cb7c70143d2aedb4d35
+  requires_dist:
+  - anyio>=3.5.0,<5
+  - distro>=1.7.0,<2
+  - httpx>=0.23.0,<1
+  - jiter>=0.4.0,<1
+  - pydantic>=1.9.0,<3
+  - sniffio
+  - typing-extensions>=4.10,<5
+  - boto3>=1.28.57 ; extra == 'bedrock'
+  - botocore>=1.31.57 ; extra == 'bedrock'
+  - google-auth>=2,<3 ; extra == 'vertex'
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/46/eb/e7f063ad1fec6b3178a3cd82d1a3c4de82cccf283fc42746168188e1cdd5/anyio-4.8.0-py3-none-any.whl
+  name: anyio
+  version: 4.8.0
+  sha256: b5011f270ab5eb0abf13385f851315585cc37ef330dd88e27ec3d34d651fd47a
+  requires_dist:
+  - exceptiongroup>=1.0.2 ; python_full_version < '3.11'
+  - idna>=2.8
+  - sniffio>=1.1
+  - typing-extensions>=4.5 ; python_full_version < '3.13'
+  - trio>=0.26.1 ; extra == 'trio'
+  - anyio[trio] ; extra == 'test'
+  - coverage[toml]>=7 ; extra == 'test'
+  - exceptiongroup>=1.2.0 ; extra == 'test'
+  - hypothesis>=4.0 ; extra == 'test'
+  - psutil>=5.9 ; extra == 'test'
+  - pytest>=7.0 ; extra == 'test'
+  - trustme ; extra == 'test'
+  - truststore>=0.9.1 ; python_full_version >= '3.10' and extra == 'test'
+  - uvloop>=0.21 ; python_full_version < '3.14' and platform_python_implementation == 'CPython' and platform_system != 'Windows' and extra == 'test'
+  - packaging ; extra == 'doc'
+  - sphinx~=7.4 ; extra == 'doc'
+  - sphinx-rtd-theme ; extra == 'doc'
+  - sphinx-autodoc-typehints>=1.2.0 ; extra == 'doc'
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/fc/30/d4986a882011f9df997a55e6becd864812ccfcd821d64aac8570ee39f719/attrs-25.1.0-py3-none-any.whl
+  name: attrs
+  version: 25.1.0
+  sha256: c75a69e28a550a7e93789579c22aa26b0f5b83b75dc4e08fe092980051e1090a
+  requires_dist:
+  - cloudpickle ; platform_python_implementation == 'CPython' and extra == 'benchmark'
+  - hypothesis ; extra == 'benchmark'
+  - mypy>=1.11.1 ; python_full_version >= '3.10' and platform_python_implementation == 'CPython' and extra == 'benchmark'
+  - pympler ; extra == 'benchmark'
+  - pytest-codspeed ; extra == 'benchmark'
+  - pytest-mypy-plugins ; python_full_version >= '3.10' and platform_python_implementation == 'CPython' and extra == 'benchmark'
+  - pytest-xdist[psutil] ; extra == 'benchmark'
+  - pytest>=4.3.0 ; extra == 'benchmark'
+  - cloudpickle ; platform_python_implementation == 'CPython' and extra == 'cov'
+  - coverage[toml]>=5.3 ; extra == 'cov'
+  - hypothesis ; extra == 'cov'
+  - mypy>=1.11.1 ; python_full_version >= '3.10' and platform_python_implementation == 'CPython' and extra == 'cov'
+  - pympler ; extra == 'cov'
+  - pytest-mypy-plugins ; python_full_version >= '3.10' and platform_python_implementation == 'CPython' and extra == 'cov'
+  - pytest-xdist[psutil] ; extra == 'cov'
+  - pytest>=4.3.0 ; extra == 'cov'
+  - cloudpickle ; platform_python_implementation == 'CPython' and extra == 'dev'
+  - hypothesis ; extra == 'dev'
+  - mypy>=1.11.1 ; python_full_version >= '3.10' and platform_python_implementation == 'CPython' and extra == 'dev'
+  - pre-commit-uv ; extra == 'dev'
+  - pympler ; extra == 'dev'
+  - pytest-mypy-plugins ; python_full_version >= '3.10' and platform_python_implementation == 'CPython' and extra == 'dev'
+  - pytest-xdist[psutil] ; extra == 'dev'
+  - pytest>=4.3.0 ; extra == 'dev'
+  - cogapp ; extra == 'docs'
+  - furo ; extra == 'docs'
+  - myst-parser ; extra == 'docs'
+  - sphinx ; extra == 'docs'
+  - sphinx-notfound-page ; extra == 'docs'
+  - sphinxcontrib-towncrier ; extra == 'docs'
+  - towncrier<24.7 ; extra == 'docs'
+  - cloudpickle ; platform_python_implementation == 'CPython' and extra == 'tests'
+  - hypothesis ; extra == 'tests'
+  - mypy>=1.11.1 ; python_full_version >= '3.10' and platform_python_implementation == 'CPython' and extra == 'tests'
+  - pympler ; extra == 'tests'
+  - pytest-mypy-plugins ; python_full_version >= '3.10' and platform_python_implementation == 'CPython' and extra == 'tests'
+  - pytest-xdist[psutil] ; extra == 'tests'
+  - pytest>=4.3.0 ; extra == 'tests'
+  - mypy>=1.11.1 ; python_full_version >= '3.10' and platform_python_implementation == 'CPython' and extra == 'tests-mypy'
+  - pytest-mypy-plugins ; python_full_version >= '3.10' and platform_python_implementation == 'CPython' and extra == 'tests-mypy'
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/52/bb/ef7a29f5717cca646be6698d80e542446a6a442be897c8f67bf93551c672/azure_cognitiveservices_speech-1.42.0-py3-none-win_amd64.whl
+  name: azure-cognitiveservices-speech
+  version: 1.42.0
+  sha256: 32076ee03b3b402a2e8841f2c21e5cd54dc3ffbf5af183426344727298c8bbd4
+  requires_python: '>=3.7'
+- pypi: https://files.pythonhosted.org/packages/83/f7/9241ad7154e554730ea56271e14ad1115c278b26a81eb892eac16fabb480/azure_cognitiveservices_speech-1.42.0-py3-none-manylinux1_x86_64.whl
+  name: azure-cognitiveservices-speech
+  version: 1.42.0
+  sha256: 90890a147499239f37b0b1a5112c51820b90fa2b5adafa0df4da6cc0c211887f
+  requires_python: '>=3.7'
+- conda: https://conda.anaconda.org/conda-forge/linux-64/bzip2-1.0.8-h4bc722e_7.conda
+  sha256: 5ced96500d945fb286c9c838e54fa759aa04a7129c59800f0846b4335cee770d
+  md5: 62ee74e96c5ebb0af99386de58cf9553
+  depends:
+  - __glibc >=2.17,<3.0.a0
+  - libgcc-ng >=12
+  license: bzip2-1.0.6
+  license_family: BSD
+  purls: []
+  size: 252783
+  timestamp: 1720974456583
+- conda: https://conda.anaconda.org/conda-forge/win-64/bzip2-1.0.8-h2466b09_7.conda
+  sha256: 35a5dad92e88fdd7fc405e864ec239486f4f31eec229e31686e61a140a8e573b
+  md5: 276e7ffe9ffe39688abc665ef0f45596
+  depends:
+  - ucrt >=10.0.20348.0
+  - vc >=14.2,<15
+  - vc14_runtime >=14.29.30139
+  license: bzip2-1.0.6
+  license_family: BSD
+  purls: []
+  size: 54927
+  timestamp: 1720974860185
+- conda: https://conda.anaconda.org/conda-forge/linux-64/ca-certificates-2025.1.31-hbcca054_0.conda
+  sha256: bf832198976d559ab44d6cdb315642655547e26d826e34da67cbee6624cda189
+  md5: 19f3a56f68d2fd06c516076bff482c52
+  license: ISC
+  purls: []
+  size: 158144
+  timestamp: 1738298224464
+- conda: https://conda.anaconda.org/conda-forge/win-64/ca-certificates-2025.1.31-h56e8100_0.conda
+  sha256: 1bedccdf25a3bd782d6b0e57ddd97cdcda5501716009f2de4479a779221df155
+  md5: 5304a31607974dfc2110dfbb662ed092
+  license: ISC
+  purls: []
+  size: 158690
+  timestamp: 1738298232550
+- pypi: https://files.pythonhosted.org/packages/38/fc/bce832fd4fd99766c04d1ee0eead6b0ec6486fb100ae5e74c1d91292b982/certifi-2025.1.31-py3-none-any.whl
+  name: certifi
+  version: 2025.1.31
+  sha256: ca78db4565a652026a4db2bcdf68f2fb589ea80d0be70e03929ed730746b84fe
+  requires_python: '>=3.6'
+- pypi: https://files.pythonhosted.org/packages/50/b9/db34c4755a7bd1cb2d1603ac3863f22bcecbd1ba29e5ee841a4bc510b294/cffi-1.17.1-cp312-cp312-win_amd64.whl
+  name: cffi
+  version: 1.17.1
+  sha256: 51392eae71afec0d0c8fb1a53b204dbb3bcabcb3c9b807eedf3e1e6ccf2de903
+  requires_dist:
+  - pycparser
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/b2/d5/da47df7004cb17e4955df6a43d14b3b4ae77737dff8bf7f8f333196717bf/cffi-1.17.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: cffi
+  version: 1.17.1
+  sha256: b62ce867176a75d03a665bad002af8e6d54644fad99a3c70905c543130e39d93
+  requires_dist:
+  - pycparser
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/38/6f/f5fbc992a329ee4e0f288c1fe0e2ad9485ed064cac731ed2fe47dcc38cbf/chardet-5.2.0-py3-none-any.whl
+  name: chardet
+  version: 5.2.0
+  sha256: e1cf59446890a00105fe7b7912492ea04b6e6f06d4b742b2c788469e34c82970
+  requires_python: '>=3.7'
+- pypi: https://files.pythonhosted.org/packages/21/5b/1b390b03b1d16c7e382b561c5329f83cc06623916aab983e8ab9239c7d5c/charset_normalizer-3.4.1-cp312-cp312-win_amd64.whl
+  name: charset-normalizer
+  version: 3.4.1
+  sha256: 6ff8a4a60c227ad87030d76e99cd1698345d4491638dfa6673027c48b3cd395f
+  requires_python: '>=3.7'
+- pypi: https://files.pythonhosted.org/packages/3e/a2/513f6cbe752421f16d969e32f3583762bfd583848b763913ddab8d9bfd4f/charset_normalizer-3.4.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: charset-normalizer
+  version: 3.4.1
+  sha256: bc2722592d8998c870fa4e290c2eec2c1569b87fe58618e67d38b4665dfa680d
+  requires_python: '>=3.7'
+- pypi: https://files.pythonhosted.org/packages/7e/d4/7ebdbd03970677812aac39c869717059dbb71a4cfc033ca6e5221787892c/click-8.1.8-py3-none-any.whl
+  name: click
+  version: 8.1.8
+  sha256: 63c132bbbed01578a06712a2d1f497bb62d9c1c0d329b7903a866228027263b2
+  requires_dist:
+  - colorama ; platform_system == 'Windows'
+  - importlib-metadata ; python_full_version < '3.8'
+  requires_python: '>=3.7'
+- pypi: https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl
+  name: colorama
+  version: 0.4.6
+  sha256: 4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6
+  requires_python: '>=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*'
+- pypi: https://files.pythonhosted.org/packages/a7/06/3d6badcf13db419e25b07041d9c7b4a2c331d3f4e7134445ec5df57714cd/coloredlogs-15.0.1-py2.py3-none-any.whl
+  name: coloredlogs
+  version: 15.0.1
+  sha256: 612ee75c546f53e92e70049c9dbfcc18c935a2b9a53b66085ce9ef6a6e5c0934
+  requires_dist:
+  - humanfriendly>=9.1
+  - capturer>=2.4 ; extra == 'cron'
+  requires_python: '>=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*'
+- pypi: https://files.pythonhosted.org/packages/4c/44/72009bb0a0d8286f6408c9cb70552350e21e9c280bfa1ef30784b30dfc0f/comtypes-1.4.10-py3-none-any.whl
+  name: comtypes
+  version: 1.4.10
+  sha256: e078555721ee7ab40648a3363697d420b845b323e5944b55846e96aff97d2534
+  requires_python: '>=3.8'
+- conda: https://conda.anaconda.org/conda-forge/noarch/cuda-version-11.8-h70ddcb2_3.conda
+  sha256: 53e0ffc14ea2f2b8c12320fd2aa38b01112763eba851336ff5953b436ae61259
+  md5: 670f0e1593b8c1d84f57ad5fe5256799
+  constrains:
+  - cudatoolkit 11.8|11.8.*
+  - __cuda >=11
+  license: LicenseRef-NVIDIA-End-User-License-Agreement
+  purls: []
+  size: 21043
+  timestamp: 1709765911943
+- conda: https://conda.anaconda.org/conda-forge/linux-64/cudatoolkit-11.8.0-h4ba93d1_13.conda
+  sha256: 1797bacaf5350f272413c7f50787c01aef0e8eb955df0f0db144b10be2819752
+  md5: eb43f5f1f16e2fad2eba22219c3e499b
+  depends:
+  - __glibc >=2.17,<3.0.a0
+  - libgcc-ng >=12
+  - libstdcxx-ng >=12
+  constrains:
+  - __cuda >=11
+  license: LicenseRef-NVIDIA-End-User-License-Agreement
+  purls: []
+  size: 715605660
+  timestamp: 1706881738892
+- conda: https://conda.anaconda.org/conda-forge/win-64/cudatoolkit-11.8.0-h09e9e62_13.conda
+  sha256: 45491dddc59d4ae8abba3640056da3c3a81b93e87a5b56f336f5ffabf58d14b3
+  md5: 56d440fefc5a01e631bbdb9e1f1701ad
+  depends:
+  - ucrt >=10.0.20348.0
+  - vc >=14.2,<15
+  - vc14_runtime >=14.29.30139
+  constrains:
+  - __cuda >=11
+  license: LicenseRef-NVIDIA-End-User-License-Agreement
+  purls: []
+  size: 726105666
+  timestamp: 1706883637901
+- conda: https://conda.anaconda.org/conda-forge/linux-64/cudnn-8.9.7.29-hbc23b4c_3.conda
+  sha256: c553234d447d9938556f067aba7a4686c8e5427e03e740e67199da3782cc420c
+  md5: 4a2d5fab2871d95544de4e1752948d0f
+  depends:
+  - __glibc >=2.17
+  - __glibc >=2.17,<3.0.a0
+  - cuda-version >=11.0,<12.0a0
+  - cudatoolkit 11.*
+  - libgcc-ng >=12
+  - libstdcxx-ng >=12
+  - libzlib >=1.2.13,<2.0.0a0
+  license: LicenseRef-cuDNN-Software-License-Agreement
+  purls: []
+  size: 465458543
+  timestamp: 1710307873021
+- conda: https://conda.anaconda.org/conda-forge/win-64/cudnn-8.9.7.29-he6de189_3.conda
+  sha256: 140b25e4df96d317de8a2ebf744b9e8e763a8a146acfdd8acd411659c6dafd80
+  md5: 083d66898b460391c0b912e92e141250
+  depends:
+  - cuda-version >=11.0,<12.0a0
+  - cudatoolkit 11.*
+  - libzlib-wapi >=1.2.13,<1.3.0a0
+  - ucrt >=10.0.20348.0
+  - vc >=14.2,<15
+  - vc14_runtime >=14.29.30139
+  license: LicenseRef-cuDNN-Software-License-Agreement
+  purls: []
+  size: 458138472
+  timestamp: 1710308712723
+- pypi: https://files.pythonhosted.org/packages/12/b3/231ffd4ab1fc9d679809f356cebee130ac7daa00d6d6f3206dd4fd137e9e/distro-1.9.0-py3-none-any.whl
+  name: distro
+  version: 1.9.0
+  sha256: 7bffd925d65168f85027d8da9af6bddab658135b840670a223589bc0c8ef02b2
+  requires_python: '>=3.6'
+- pypi: https://files.pythonhosted.org/packages/f8/37/00c211f1021f9b04dde72dcbee72ce66248519c3899a47b06f8940a67c08/edge_tts-7.0.0-py3-none-any.whl
+  name: edge-tts
+  version: 7.0.0
+  sha256: c99e91caba83c28e6f1fff1098a8188f541ba9615944c7a6f8f5625e02848044
+  requires_dist:
+  - aiohttp>=3.8.0,<4.0.0
+  - certifi>=2023.11.17
+  - srt>=3.4.1,<4.0.0
+  - tabulate>=0.4.4,<1.0.0
+  - typing-extensions>=4.1.0,<5.0.0
+  - black ; extra == 'dev'
+  - isort ; extra == 'dev'
+  - mypy ; extra == 'dev'
+  - pylint ; extra == 'dev'
+  - types-tabulate ; extra == 'dev'
+  requires_python: '>=3.7'
+- pypi: https://files.pythonhosted.org/packages/8f/7d/2d6ce181d7a5f51dedb8c06206cbf0ec026a99bf145edd309f9e17c3282f/fastapi-0.115.8-py3-none-any.whl
+  name: fastapi
+  version: 0.115.8
+  sha256: 753a96dd7e036b34eeef8babdfcfe3f28ff79648f86551eb36bfc1b0bf4a8cbf
+  requires_dist:
+  - starlette>=0.40.0,<0.46.0
+  - pydantic>=1.7.4,!=1.8,!=1.8.1,!=2.0.0,!=2.0.1,!=2.1.0,<3.0.0
+  - typing-extensions>=4.8.0
+  - fastapi-cli[standard]>=0.0.5 ; extra == 'standard'
+  - httpx>=0.23.0 ; extra == 'standard'
+  - jinja2>=3.1.5 ; extra == 'standard'
+  - python-multipart>=0.0.18 ; extra == 'standard'
+  - email-validator>=2.0.0 ; extra == 'standard'
+  - uvicorn[standard]>=0.12.0 ; extra == 'standard'
+  - fastapi-cli[standard]>=0.0.5 ; extra == 'all'
+  - httpx>=0.23.0 ; extra == 'all'
+  - jinja2>=3.1.5 ; extra == 'all'
+  - python-multipart>=0.0.18 ; extra == 'all'
+  - itsdangerous>=1.1.0 ; extra == 'all'
+  - pyyaml>=5.3.1 ; extra == 'all'
+  - ujson>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0 ; extra == 'all'
+  - orjson>=3.2.1 ; extra == 'all'
+  - email-validator>=2.0.0 ; extra == 'all'
+  - uvicorn[standard]>=0.12.0 ; extra == 'all'
+  - pydantic-settings>=2.0.0 ; extra == 'all'
+  - pydantic-extra-types>=2.0.0 ; extra == 'all'
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/0e/e2/b066e6e02d67bf5261a6d7539648c6da3365cc9eff3eb6d82009595d84d9/flatbuffers-25.1.24-py2.py3-none-any.whl
+  name: flatbuffers
+  version: 25.1.24
+  sha256: 1abfebaf4083117225d0723087ea909896a34e3fec933beedb490d595ba24145
+- pypi: https://files.pythonhosted.org/packages/af/f2/64b73a9bb86f5a89fb55450e97cd5c1f84a862d4ff90d9fd1a73ab0f64a5/frozenlist-1.5.0-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: frozenlist
+  version: 1.5.0
+  sha256: 000a77d6034fbad9b6bb880f7ec073027908f1b40254b5d6f26210d2dab1240e
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/b1/56/4e45136ffc6bdbfa68c29ca56ef53783ef4c2fd395f7cbf99a2624aa9aaa/frozenlist-1.5.0-cp312-cp312-win_amd64.whl
+  name: frozenlist
+  version: 1.5.0
+  sha256: 8969190d709e7c48ea386db202d708eb94bdb29207a1f269bab1196ce0dcca1f
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/b0/6c/5a53d632b44ef7655ac8d9b34432e13160917f9307c94b1467efd34e336e/groq-0.18.0-py3-none-any.whl
+  name: groq
+  version: 0.18.0
+  sha256: 81d5ac00057a45d8ce559d23ab5d3b3893011d1f12c35187ab35a9182d826ea6
+  requires_dist:
+  - anyio>=3.5.0,<5
+  - distro>=1.7.0,<2
+  - httpx>=0.23.0,<1
+  - pydantic>=1.9.0,<3
+  - sniffio
+  - typing-extensions>=4.10,<5
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/95/04/ff642e65ad6b90db43e668d70ffb6736436c7ce41fcc549f4e9472234127/h11-0.14.0-py3-none-any.whl
+  name: h11
+  version: 0.14.0
+  sha256: e3fe4ac4b851c468cc8363d500db52c2ead036020723024a109d37346efaa761
+  requires_dist:
+  - typing-extensions ; python_full_version < '3.8'
+  requires_python: '>=3.7'
+- pypi: https://files.pythonhosted.org/packages/87/f5/72347bc88306acb359581ac4d52f23c0ef445b57157adedb9aee0cd689d2/httpcore-1.0.7-py3-none-any.whl
+  name: httpcore
+  version: 1.0.7
+  sha256: a3fff8f43dc260d5bd363d9f9cf1830fa3a458b332856f34282de498ed420edd
+  requires_dist:
+  - certifi
+  - h11>=0.13,<0.15
+  - anyio>=4.0,<5.0 ; extra == 'asyncio'
+  - h2>=3,<5 ; extra == 'http2'
+  - socksio==1.* ; extra == 'socks'
+  - trio>=0.22.0,<1.0 ; extra == 'trio'
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/12/b7/5cae71a8868e555f3f67a50ee7f673ce36eac970f029c0c5e9d584352961/httptools-0.6.4-cp312-cp312-win_amd64.whl
+  name: httptools
+  version: 0.6.4
+  sha256: db78cb9ca56b59b016e64b6031eda5653be0589dba2b1b43453f6e8b405a0970
+  requires_dist:
+  - cython>=0.29.24 ; extra == 'test'
+  requires_python: '>=3.8.0'
+- pypi: https://files.pythonhosted.org/packages/f7/d8/b644c44acc1368938317d76ac991c9bba1166311880bcc0ac297cb9d6bd7/httptools-0.6.4-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: httptools
+  version: 0.6.4
+  sha256: 16e603a3bff50db08cd578d54f07032ca1631450ceb972c2f834c2b860c28ea2
+  requires_dist:
+  - cython>=0.29.24 ; extra == 'test'
+  requires_python: '>=3.8.0'
+- pypi: https://files.pythonhosted.org/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl
+  name: httpx
+  version: 0.28.1
+  sha256: d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad
+  requires_dist:
+  - anyio
+  - certifi
+  - httpcore==1.*
+  - idna
+  - brotli ; platform_python_implementation == 'CPython' and extra == 'brotli'
+  - brotlicffi ; platform_python_implementation != 'CPython' and extra == 'brotli'
+  - click==8.* ; extra == 'cli'
+  - pygments==2.* ; extra == 'cli'
+  - rich>=10,<14 ; extra == 'cli'
+  - h2>=3,<5 ; extra == 'http2'
+  - socksio==1.* ; extra == 'socks'
+  - zstandard>=0.18.0 ; extra == 'zstd'
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/f0/0f/310fb31e39e2d734ccaa2c0fb981ee41f7bd5056ce9bc29b2248bd569169/humanfriendly-10.0-py2.py3-none-any.whl
+  name: humanfriendly
+  version: '10.0'
+  sha256: 1697e1a8a8f550fd43c2865cd84542fc175a61dcb779b6fee18cf6b6ccba1477
+  requires_dist:
+  - monotonic ; python_full_version == '2.7.*'
+  - pyreadline ; python_full_version < '3.8' and sys_platform == 'win32'
+  - pyreadline3 ; python_full_version >= '3.8' and sys_platform == 'win32'
+  requires_python: '>=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*'
+- pypi: https://files.pythonhosted.org/packages/76/c6/c88e154df9c4e1a2a66ccf0005a88dfb2650c1dffb6f5ce603dfbd452ce3/idna-3.10-py3-none-any.whl
+  name: idna
+  version: '3.10'
+  sha256: 946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3
+  requires_dist:
+  - ruff>=0.6.2 ; extra == 'all'
+  - mypy>=1.11.2 ; extra == 'all'
+  - pytest>=8.3.2 ; extra == 'all'
+  - flake8>=7.1.1 ; extra == 'all'
+  requires_python: '>=3.6'
+- pypi: https://files.pythonhosted.org/packages/17/61/beea645c0bf398ced8b199e377b61eb999d8e46e053bb285c91c3d3eaab0/jiter-0.8.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: jiter
+  version: 0.8.2
+  sha256: 14601dcac4889e0a1c75ccf6a0e4baf70dbc75041e51bcf8d0e9274519df6887
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/41/69/6d4bbe66b3b3b4507e47aa1dd5d075919ad242b4b1115b3f80eecd443687/jiter-0.8.2-cp312-cp312-win_amd64.whl
+  name: jiter
+  version: 0.8.2
+  sha256: 83c0efd80b29695058d0fd2fa8a556490dbce9804eac3e281f373bbc99045f6c
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/0e/72/a3add0e4eec4eb9e2569554f7c70f4a3c27712f40e3284d483e88094cc0e/langdetect-1.0.9.tar.gz
+  name: langdetect
+  version: 1.0.9
+  sha256: cbc1fef89f8d062739774bd51eda3da3274006b3661d199c2655f6b3f6d605a0
+  requires_dist:
+  - six
+- conda: https://conda.anaconda.org/conda-forge/linux-64/ld_impl_linux-64-2.43-h712a8e2_2.conda
+  sha256: 7c91cea91b13f4314d125d1bedb9d03a29ebbd5080ccdea70260363424646dbe
+  md5: 048b02e3962f066da18efe3a21b77672
+  depends:
+  - __glibc >=2.17,<3.0.a0
+  constrains:
+  - binutils_impl_linux-64 2.43
+  license: GPL-3.0-only
+  license_family: GPL
+  purls: []
+  size: 669211
+  timestamp: 1729655358674
+- conda: https://conda.anaconda.org/conda-forge/linux-64/libexpat-2.6.4-h5888daf_0.conda
+  sha256: 56541b98447b58e52d824bd59d6382d609e11de1f8adf20b23143e353d2b8d26
+  md5: db833e03127376d461e1e13e76f09b6c
+  depends:
+  - __glibc >=2.17,<3.0.a0
+  - libgcc >=13
+  constrains:
+  - expat 2.6.4.*
+  license: MIT
+  license_family: MIT
+  purls: []
+  size: 73304
+  timestamp: 1730967041968
+- conda: https://conda.anaconda.org/conda-forge/win-64/libexpat-2.6.4-he0c23c2_0.conda
+  sha256: 0c0447bf20d1013d5603499de93a16b6faa92d7ead870d96305c0f065b6a5a12
+  md5: eb383771c680aa792feb529eaf9df82f
+  depends:
+  - ucrt >=10.0.20348.0
+  - vc >=14.2,<15
+  - vc14_runtime >=14.29.30139
+  constrains:
+  - expat 2.6.4.*
+  license: MIT
+  license_family: MIT
+  purls: []
+  size: 139068
+  timestamp: 1730967442102
+- conda: https://conda.anaconda.org/conda-forge/linux-64/libffi-3.4.2-h7f98852_5.tar.bz2
+  sha256: ab6e9856c21709b7b517e940ae7028ae0737546122f83c2aa5d692860c3b149e
+  md5: d645c6d2ac96843a2bfaccd2d62b3ac3
+  depends:
+  - libgcc-ng >=9.4.0
+  license: MIT
+  license_family: MIT
+  purls: []
+  size: 58292
+  timestamp: 1636488182923
+- conda: https://conda.anaconda.org/conda-forge/win-64/libffi-3.4.2-h8ffe710_5.tar.bz2
+  sha256: 1951ab740f80660e9bc07d2ed3aefb874d78c107264fd810f24a1a6211d4b1a5
+  md5: 2c96d1b6915b408893f9472569dee135
+  depends:
+  - vc >=14.1,<15.0a0
+  - vs2015_runtime >=14.16.27012
+  license: MIT
+  license_family: MIT
+  purls: []
+  size: 42063
+  timestamp: 1636489106777
+- conda: https://conda.anaconda.org/conda-forge/linux-64/libgcc-14.2.0-h77fa898_1.conda
+  sha256: 53eb8a79365e58849e7b1a068d31f4f9e718dc938d6f2c03e960345739a03569
+  md5: 3cb76c3f10d3bc7f1105b2fc9db984df
+  depends:
+  - _libgcc_mutex 0.1 conda_forge
+  - _openmp_mutex >=4.5
+  constrains:
+  - libgomp 14.2.0 h77fa898_1
+  - libgcc-ng ==14.2.0=*_1
+  license: GPL-3.0-only WITH GCC-exception-3.1
+  license_family: GPL
+  purls: []
+  size: 848745
+  timestamp: 1729027721139
+- conda: https://conda.anaconda.org/conda-forge/linux-64/libgcc-ng-14.2.0-h69a702a_1.conda
+  sha256: 3a76969c80e9af8b6e7a55090088bc41da4cffcde9e2c71b17f44d37b7cb87f7
+  md5: e39480b9ca41323497b05492a63bc35b
+  depends:
+  - libgcc 14.2.0 h77fa898_1
+  license: GPL-3.0-only WITH GCC-exception-3.1
+  license_family: GPL
+  purls: []
+  size: 54142
+  timestamp: 1729027726517
+- conda: https://conda.anaconda.org/conda-forge/linux-64/libgomp-14.2.0-h77fa898_1.conda
+  sha256: 1911c29975ec99b6b906904040c855772ccb265a1c79d5d75c8ceec4ed89cd63
+  md5: cc3573974587f12dda90d96e3e55a702
+  depends:
+  - _libgcc_mutex 0.1 conda_forge
+  license: GPL-3.0-only WITH GCC-exception-3.1
+  license_family: GPL
+  purls: []
+  size: 460992
+  timestamp: 1729027639220
+- conda: https://conda.anaconda.org/conda-forge/linux-64/liblzma-5.6.4-hb9d3cd8_0.conda
+  sha256: cad52e10319ca4585bc37f0bc7cce99ec7c15dc9168e42ccb96b741b0a27db3f
+  md5: 42d5b6a0f30d3c10cd88cb8584fda1cb
+  depends:
+  - __glibc >=2.17,<3.0.a0
+  - libgcc >=13
+  license: 0BSD
+  purls: []
+  size: 111357
+  timestamp: 1738525339684
+- conda: https://conda.anaconda.org/conda-forge/win-64/liblzma-5.6.4-h2466b09_0.conda
+  sha256: 3f552b0bdefdd1459ffc827ea3bf70a6a6920c7879d22b6bfd0d73015b55227b
+  md5: c48f6ad0ef0a555b27b233dfcab46a90
+  depends:
+  - ucrt >=10.0.20348.0
+  - vc >=14.2,<15
+  - vc14_runtime >=14.29.30139
+  license: 0BSD
+  purls: []
+  size: 104465
+  timestamp: 1738525557254
+- conda: https://conda.anaconda.org/conda-forge/linux-64/libnsl-2.0.1-hd590300_0.conda
+  sha256: 26d77a3bb4dceeedc2a41bd688564fe71bf2d149fdcf117049970bc02ff1add6
+  md5: 30fd6e37fe21f86f4bd26d6ee73eeec7
+  depends:
+  - libgcc-ng >=12
+  license: LGPL-2.1-only
+  license_family: GPL
+  purls: []
+  size: 33408
+  timestamp: 1697359010159
+- conda: https://conda.anaconda.org/conda-forge/linux-64/libsqlite-3.49.0-hee588c1_0.conda
+  sha256: 51c68794a1f32c2742cbcfc8ea8cd730bb19148bed437197380778d3a6d49385
+  md5: a12aa55f2a4446af8aa44d69ac563d58
+  depends:
+  - __glibc >=2.17,<3.0.a0
+  - libgcc >=13
+  - libzlib >=1.3.1,<2.0a0
+  license: Unlicense
+  purls: []
+  size: 917347
+  timestamp: 1739176276854
+- conda: https://conda.anaconda.org/conda-forge/win-64/libsqlite-3.49.0-h67fdade_0.conda
+  sha256: ff6670afcef19234145cd7e2e3b97a6a591a09f2b98d0920b140bf175979db47
+  md5: b5aae7f19da05cb648ca214bf14ddd81
+  depends:
+  - ucrt >=10.0.20348.0
+  - vc >=14.2,<15
+  - vc14_runtime >=14.29.30139
+  license: Unlicense
+  purls: []
+  size: 1082337
+  timestamp: 1739176678486
+- conda: https://conda.anaconda.org/conda-forge/linux-64/libstdcxx-14.2.0-hc0a3c3a_1.conda
+  sha256: 4661af0eb9bdcbb5fb33e5d0023b001ad4be828fccdcc56500059d56f9869462
+  md5: 234a5554c53625688d51062645337328
+  depends:
+  - libgcc 14.2.0 h77fa898_1
+  license: GPL-3.0-only WITH GCC-exception-3.1
+  license_family: GPL
+  purls: []
+  size: 3893695
+  timestamp: 1729027746910
+- conda: https://conda.anaconda.org/conda-forge/linux-64/libstdcxx-ng-14.2.0-h4852527_1.conda
+  sha256: 25bb30b827d4f6d6f0522cc0579e431695503822f144043b93c50237017fffd8
+  md5: 8371ac6457591af2cf6159439c1fd051
+  depends:
+  - libstdcxx 14.2.0 hc0a3c3a_1
+  license: GPL-3.0-only WITH GCC-exception-3.1
+  license_family: GPL
+  purls: []
+  size: 54105
+  timestamp: 1729027780628
+- conda: https://conda.anaconda.org/conda-forge/linux-64/libuuid-2.38.1-h0b41bf4_0.conda
+  sha256: 787eb542f055a2b3de553614b25f09eefb0a0931b0c87dbcce6efdfd92f04f18
+  md5: 40b61aab5c7ba9ff276c41cfffe6b80b
+  depends:
+  - libgcc-ng >=12
+  license: BSD-3-Clause
+  license_family: BSD
+  purls: []
+  size: 33601
+  timestamp: 1680112270483
+- conda: https://conda.anaconda.org/conda-forge/linux-64/libxcrypt-4.4.36-hd590300_1.conda
+  sha256: 6ae68e0b86423ef188196fff6207ed0c8195dd84273cb5623b85aa08033a410c
+  md5: 5aa797f8787fe7a17d1b0821485b5adc
+  depends:
+  - libgcc-ng >=12
+  license: LGPL-2.1-or-later
+  purls: []
+  size: 100393
+  timestamp: 1702724383534
+- conda: https://conda.anaconda.org/conda-forge/linux-64/libzlib-1.3.1-hb9d3cd8_2.conda
+  sha256: d4bfe88d7cb447768e31650f06257995601f89076080e76df55e3112d4e47dc4
+  md5: edb0dca6bc32e4f4789199455a1dbeb8
+  depends:
+  - __glibc >=2.17,<3.0.a0
+  - libgcc >=13
+  constrains:
+  - zlib 1.3.1 *_2
+  license: Zlib
+  license_family: Other
+  purls: []
+  size: 60963
+  timestamp: 1727963148474
+- conda: https://conda.anaconda.org/conda-forge/win-64/libzlib-1.3.1-h2466b09_2.conda
+  sha256: ba945c6493449bed0e6e29883c4943817f7c79cbff52b83360f7b341277c6402
+  md5: 41fbfac52c601159df6c01f875de31b9
+  depends:
+  - ucrt >=10.0.20348.0
+  - vc >=14.2,<15
+  - vc14_runtime >=14.29.30139
+  constrains:
+  - zlib 1.3.1 *_2
+  license: Zlib
+  license_family: Other
+  purls: []
+  size: 55476
+  timestamp: 1727963768015
+- conda: https://conda.anaconda.org/conda-forge/win-64/libzlib-wapi-1.2.13-h2466b09_6.conda
+  sha256: dd92ecd1f39e17623fd6149cf0dc7f675d2f9e091ef2b1774a85e9e545434102
+  md5: 84ac5ada002445227139f8f659cf6d93
+  depends:
+  - ucrt >=10.0.20348.0
+  - vc >=14.2,<15
+  - vc14_runtime >=14.29.30139
+  constrains:
+  - zlib-wapi 1.2.13 *_6
+  - zlib 1.2.13 *_6
+  license: Zlib
+  license_family: Other
+  purls: []
+  size: 56048
+  timestamp: 1716874638604
+- pypi: https://files.pythonhosted.org/packages/0c/29/0348de65b8cc732daa3e33e67806420b2ae89bdce2b04af740289c5c6c8c/loguru-0.7.3-py3-none-any.whl
+  name: loguru
+  version: 0.7.3
+  sha256: 31a33c10c8e1e10422bfd431aeb5d351c7cf7fa671e3c4df004162264b28220c
+  requires_dist:
+  - colorama>=0.3.4 ; sys_platform == 'win32'
+  - aiocontextvars>=0.2.0 ; python_full_version < '3.7'
+  - win32-setctime>=1.0.0 ; sys_platform == 'win32'
+  - pre-commit==4.0.1 ; python_full_version >= '3.9' and extra == 'dev'
+  - tox==3.27.1 ; python_full_version < '3.8' and extra == 'dev'
+  - tox==4.23.2 ; python_full_version >= '3.8' and extra == 'dev'
+  - pytest==6.1.2 ; python_full_version < '3.8' and extra == 'dev'
+  - pytest==8.3.2 ; python_full_version >= '3.8' and extra == 'dev'
+  - pytest-cov==2.12.1 ; python_full_version < '3.8' and extra == 'dev'
+  - pytest-cov==5.0.0 ; python_full_version == '3.8.*' and extra == 'dev'
+  - pytest-cov==6.0.0 ; python_full_version >= '3.9' and extra == 'dev'
+  - pytest-mypy-plugins==1.9.3 ; python_full_version >= '3.6' and python_full_version < '3.8' and extra == 'dev'
+  - pytest-mypy-plugins==3.1.0 ; python_full_version >= '3.8' and extra == 'dev'
+  - colorama==0.4.5 ; python_full_version < '3.8' and extra == 'dev'
+  - colorama==0.4.6 ; python_full_version >= '3.8' and extra == 'dev'
+  - freezegun==1.1.0 ; python_full_version < '3.8' and extra == 'dev'
+  - freezegun==1.5.0 ; python_full_version >= '3.8' and extra == 'dev'
+  - exceptiongroup==1.1.3 ; python_full_version >= '3.7' and python_full_version < '3.11' and extra == 'dev'
+  - mypy==0.910 ; python_full_version < '3.6' and extra == 'dev'
+  - mypy==0.971 ; python_full_version == '3.6.*' and extra == 'dev'
+  - mypy==1.4.1 ; python_full_version == '3.7.*' and extra == 'dev'
+  - mypy==1.13.0 ; python_full_version >= '3.8' and extra == 'dev'
+  - sphinx==8.1.3 ; python_full_version >= '3.11' and extra == 'dev'
+  - sphinx-rtd-theme==3.0.2 ; python_full_version >= '3.11' and extra == 'dev'
+  - myst-parser==4.0.0 ; python_full_version >= '3.11' and extra == 'dev'
+  - build==1.2.2 ; python_full_version >= '3.11' and extra == 'dev'
+  - twine==6.0.1 ; python_full_version >= '3.11' and extra == 'dev'
+  requires_python: '>=3.5,<4.0'
+- pypi: https://files.pythonhosted.org/packages/43/e3/7d92a15f894aa0c9c4b49b8ee9ac9850d6e63b03c9c32c0367a13ae62209/mpmath-1.3.0-py3-none-any.whl
+  name: mpmath
+  version: 1.3.0
+  sha256: a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c
+  requires_dist:
+  - pytest>=4.6 ; extra == 'develop'
+  - pycodestyle ; extra == 'develop'
+  - pytest-cov ; extra == 'develop'
+  - codecov ; extra == 'develop'
+  - wheel ; extra == 'develop'
+  - sphinx ; extra == 'docs'
+  - gmpy2>=2.1.0a4 ; platform_python_implementation != 'PyPy' and extra == 'gmpy'
+  - pytest>=4.6 ; extra == 'tests'
+- pypi: https://files.pythonhosted.org/packages/a3/bf/f332a13486b1ed0496d624bcc7e8357bb8053823e8cd4b9a18edc1d97e73/multidict-6.1.0-cp312-cp312-win_amd64.whl
+  name: multidict
+  version: 6.1.0
+  sha256: 188215fc0aafb8e03341995e7c4797860181562380f81ed0a87ff455b70bf1f1
+  requires_dist:
+  - typing-extensions>=4.1.0 ; python_full_version < '3.11'
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/d3/c8/529101d7176fe7dfe1d99604e48d69c5dfdcadb4f06561f465c8ef12b4df/multidict-6.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: multidict
+  version: 6.1.0
+  sha256: 4b820514bfc0b98a30e3d85462084779900347e4d49267f747ff54060cc33925
+  requires_dist:
+  - typing-extensions>=4.1.0 ; python_full_version < '3.11'
+  requires_python: '>=3.8'
+- conda: https://conda.anaconda.org/conda-forge/linux-64/ncurses-6.5-h2d0b736_3.conda
+  sha256: 3fde293232fa3fca98635e1167de6b7c7fda83caf24b9d6c91ec9eefb4f4d586
+  md5: 47e340acb35de30501a76c7c799c41d7
+  depends:
+  - __glibc >=2.17,<3.0.a0
+  - libgcc >=13
+  license: X11 AND BSD-3-Clause
+  purls: []
+  size: 891641
+  timestamp: 1738195959188
+- pypi: https://files.pythonhosted.org/packages/0f/50/de23fde84e45f5c4fda2488c759b69990fd4512387a8632860f3ac9cd225/numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: numpy
+  version: 1.26.4
+  sha256: 675d61ffbfa78604709862923189bad94014bef562cc35cf61d3a07bba02a7ed
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/16/2e/86f24451c2d530c88daf997cb8d6ac622c1d40d19f5a031ed68a4b73a374/numpy-1.26.4-cp312-cp312-win_amd64.whl
+  name: numpy
+  version: 1.26.4
+  sha256: 08beddf13648eb95f8d867350f6a018a4be2e5ad54c8d8caed89ebca558b2818
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/47/42/2f71f5680834688a9c81becbe5c5bb996fd33eaed5c66ae0606c3b1d6a02/onnxruntime-1.20.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
+  name: onnxruntime
+  version: 1.20.1
+  sha256: bb71a814f66517a65628c9e4a2bb530a6edd2cd5d87ffa0af0f6f773a027d99e
+  requires_dist:
+  - coloredlogs
+  - flatbuffers
+  - numpy>=1.21.6
+  - packaging
+  - protobuf
+  - sympy
+- pypi: https://files.pythonhosted.org/packages/dd/80/76979e0b744307d488c79e41051117634b956612cc731f1028eb17ee7294/onnxruntime-1.20.1-cp312-cp312-win_amd64.whl
+  name: onnxruntime
+  version: 1.20.1
+  sha256: 19c2d843eb074f385e8bbb753a40df780511061a63f9def1b216bf53860223fb
+  requires_dist:
+  - coloredlogs
+  - flatbuffers
+  - numpy>=1.21.6
+  - packaging
+  - protobuf
+  - sympy
+- pypi: .
+  name: open-llm-vtuber
+  version: 1.0.3
+  sha256: 006c9a1b22f28c2ed3da9a98b45007a1b13afdb34bc66a2a780355a2a6ae55d3
+  requires_dist:
+  - anthropic>=0.40.0
+  - azure-cognitiveservices-speech>=1.41.1
+  - chardet>=5.2.0
+  - edge-tts>=7.0.0
+  - fastapi>=0.115.6
+  - groq>=0.13.0
+  - httpx>=0.28.1
+  - langdetect>=1.0.9
+  - loguru>=0.7.2
+  - numpy>=1.26.4,<2
+  - onnxruntime>=1.20.1
+  - openai>=1.57.4
+  - pydub>=0.25.1
+  - pysbd>=0.3.4
+  - pyttsx3>=2.98
+  - pyyaml>=6.0.2
+  - requests>=2.32.3
+  - ruff>=0.8.6
+  - scipy>=1.14.1
+  - sherpa-onnx>=1.10.39
+  - soundfile>=0.12.1
+  - tomli>=2.2.1
+  - tqdm>=4.67.1
+  - uvicorn[standard]>=0.33.0
+  - websocket-client>=1.8.0
+  requires_python: '>=3.10,<3.13'
+  editable: true
+- pypi: https://files.pythonhosted.org/packages/9a/b6/2e2a011b2dc27a6711376808b4cd8c922c476ea0f1420b39892117fa8563/openai-1.61.1-py3-none-any.whl
+  name: openai
+  version: 1.61.1
+  sha256: 72b0826240ce26026ac2cd17951691f046e5be82ad122d20a8e1b30ca18bd11e
+  requires_dist:
+  - anyio>=3.5.0,<5
+  - distro>=1.7.0,<2
+  - httpx>=0.23.0,<1
+  - jiter>=0.4.0,<1
+  - pydantic>=1.9.0,<3
+  - sniffio
+  - tqdm>4
+  - typing-extensions>=4.11,<5
+  - numpy>=1 ; extra == 'datalib'
+  - pandas-stubs>=1.1.0.11 ; extra == 'datalib'
+  - pandas>=1.2.3 ; extra == 'datalib'
+  - websockets>=13,<15 ; extra == 'realtime'
+  requires_python: '>=3.8'
+- conda: https://conda.anaconda.org/conda-forge/linux-64/openssl-3.4.0-h7b32b05_1.conda
+  sha256: f62f6bca4a33ca5109b6d571b052a394d836956d21b25b7ffd03376abf7a481f
+  md5: 4ce6875f75469b2757a65e10a5d05e31
+  depends:
+  - __glibc >=2.17,<3.0.a0
+  - ca-certificates
+  - libgcc >=13
+  license: Apache-2.0
+  license_family: Apache
+  purls: []
+  size: 2937158
+  timestamp: 1736086387286
+- conda: https://conda.anaconda.org/conda-forge/win-64/openssl-3.4.0-ha4e3fda_1.conda
+  sha256: 519a06eaab7c878fbebb8cab98ea4a4465eafb1e9ed8c6ce67226068a80a92f0
+  md5: fb45308ba8bfe1abf1f4a27bad24a743
+  depends:
+  - ca-certificates
+  - ucrt >=10.0.20348.0
+  - vc >=14.2,<15
+  - vc14_runtime >=14.29.30139
+  license: Apache-2.0
+  license_family: Apache
+  purls: []
+  size: 8462960
+  timestamp: 1736088436984
+- pypi: https://files.pythonhosted.org/packages/88/ef/eb23f262cca3c0c4eb7ab1933c3b1f03d021f2c48f54763065b6f0e321be/packaging-24.2-py3-none-any.whl
+  name: packaging
+  version: '24.2'
+  sha256: 09abb1bccd265c01f4a3aa3f7a7db064b36514d2cba19a2f694fe6150451a759
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/1c/07/ebe102777a830bca91bbb93e3479cd34c2ca5d0361b83be9dbd93104865e/propcache-0.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: propcache
+  version: 0.2.1
+  sha256: 647894f5ae99c4cf6bb82a1bb3a796f6e06af3caa3d32e26d2350d0e3e3faf24
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/3b/77/a92c3ef994e47180862b9d7d11e37624fb1c00a16d61faf55115d970628b/propcache-0.2.1-cp312-cp312-win_amd64.whl
+  name: propcache
+  version: 0.2.1
+  sha256: c214999039d4f2a5b2073ac506bba279945233da8c786e490d411dfc30f855c1
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/61/fa/aae8e10512b83de633f2646506a6d835b151edf4b30d18d73afd01447253/protobuf-5.29.3-cp310-abi3-win_amd64.whl
+  name: protobuf
+  version: 5.29.3
+  sha256: a4fa6f80816a9a0678429e84973f2f98cbc218cca434abe8db2ad0bffc98503a
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/a8/45/2ebbde52ad2be18d3675b6bee50e68cd73c9e0654de77d595540b5129df8/protobuf-5.29.3-cp38-abi3-manylinux2014_x86_64.whl
+  name: protobuf
+  version: 5.29.3
+  sha256: c027e08a08be10b67c06bf2370b99c811c466398c357e615ca88c91c07f0910f
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/13/a3/a812df4e2dd5696d1f351d58b8fe16a405b234ad2886a0dab9183fb78109/pycparser-2.22-py3-none-any.whl
+  name: pycparser
+  version: '2.22'
+  sha256: c3702b6d3dd8c7abc1afa565d7e63d53a1d0bd86cdc24edd75470f4de499cfcc
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/f4/3c/8cc1cc84deffa6e25d2d0c688ebb80635dfdbf1dbea3e30c541c8cf4d860/pydantic-2.10.6-py3-none-any.whl
+  name: pydantic
+  version: 2.10.6
+  sha256: 427d664bf0b8a2b34ff5dd0f5a18df00591adcee7198fbd71981054cef37b584
+  requires_dist:
+  - annotated-types>=0.6.0
+  - pydantic-core==2.27.2
+  - typing-extensions>=4.12.2
+  - email-validator>=2.0.0 ; extra == 'email'
+  - tzdata ; python_full_version >= '3.9' and platform_system == 'Windows' and extra == 'timezone'
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/1f/ea/cd7209a889163b8dcca139fe32b9687dd05249161a3edda62860430457a5/pydantic_core-2.27.2-cp312-cp312-win_amd64.whl
+  name: pydantic-core
+  version: 2.27.2
+  sha256: cc3f1a99a4f4f9dd1de4fe0312c114e740b5ddead65bb4102884b384c15d8bc9
+  requires_dist:
+  - typing-extensions>=4.6.0,!=4.7.0
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/8d/f0/49129b27c43396581a635d8710dae54a791b17dfc50c70164866bbf865e3/pydantic_core-2.27.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: pydantic-core
+  version: 2.27.2
+  sha256: 6fb4aadc0b9a0c063206846d603b92030eb6f03069151a625667f982887153e2
+  requires_dist:
+  - typing-extensions>=4.6.0,!=4.7.0
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/a6/53/d78dc063216e62fc55f6b2eebb447f6a4b0a59f55c8406376f76bf959b08/pydub-0.25.1-py2.py3-none-any.whl
+  name: pydub
+  version: 0.25.1
+  sha256: 65617e33033874b59d87db603aa1ed450633288aefead953b30bded59cb599a6
+- pypi: https://files.pythonhosted.org/packages/d0/1b/2f292bbd742e369a100c91faa0483172cd91a1a422a6692055ac920946c5/pypiwin32-223-py3-none-any.whl
+  name: pypiwin32
+  version: '223'
+  sha256: 67adf399debc1d5d14dffc1ab5acacb800da569754fafdc576b2a039485aa775
+  requires_dist:
+  - pywin32>=223
+- pypi: https://files.pythonhosted.org/packages/5a/dc/491b7661614ab97483abf2056be1deee4dc2490ecbf7bff9ab5cdbac86e1/pyreadline3-3.5.4-py3-none-any.whl
+  name: pyreadline3
+  version: 3.5.4
+  sha256: eaf8e6cc3c49bcccf145fc6067ba8643d1df34d604a1ec0eccbf7a18e6d3fae6
+  requires_dist:
+  - build ; extra == 'dev'
+  - flake8 ; extra == 'dev'
+  - mypy ; extra == 'dev'
+  - pytest ; extra == 'dev'
+  - twine ; extra == 'dev'
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/48/0a/c99fb7d7e176f8b176ef19704a32e6a9c6aafdf19ef75a187f701fc15801/pysbd-0.3.4-py3-none-any.whl
+  name: pysbd
+  version: 0.3.4
+  sha256: cd838939b7b0b185fcf86b0baf6636667dfb6e474743beeff878e9f42e022953
+  requires_python: '>=3'
+- conda: https://conda.anaconda.org/conda-forge/linux-64/python-3.12.8-h9e4cc4f_1_cpython.conda
+  build_number: 1
+  sha256: 3f0e0518c992d8ccfe62b189125721309836fe48a010dc424240583e157f9ff0
+  md5: 7fd2fd79436d9b473812f14e86746844
+  depends:
+  - __glibc >=2.17,<3.0.a0
+  - bzip2 >=1.0.8,<2.0a0
+  - ld_impl_linux-64 >=2.36.1
+  - libexpat >=2.6.4,<3.0a0
+  - libffi >=3.4,<4.0a0
+  - libgcc >=13
+  - liblzma >=5.6.3,<6.0a0
+  - libnsl >=2.0.1,<2.1.0a0
+  - libsqlite >=3.47.0,<4.0a0
+  - libuuid >=2.38.1,<3.0a0
+  - libxcrypt >=4.4.36
+  - libzlib >=1.3.1,<2.0a0
+  - ncurses >=6.5,<7.0a0
+  - openssl >=3.4.0,<4.0a0
+  - readline >=8.2,<9.0a0
+  - tk >=8.6.13,<8.7.0a0
+  - tzdata
+  constrains:
+  - python_abi 3.12.* *_cp312
+  license: Python-2.0
+  purls: []
+  size: 31565686
+  timestamp: 1733410597922
+- conda: https://conda.anaconda.org/conda-forge/win-64/python-3.12.8-h3f84c4b_1_cpython.conda
+  build_number: 1
+  sha256: e1b37a398b3e2ea363de7cff6706e5ec2a5eb36b211132150e8601d7afd8f3aa
+  md5: 8cd0693344796fb32087185fca16f4cc
+  depends:
+  - bzip2 >=1.0.8,<2.0a0
+  - libexpat >=2.6.4,<3.0a0
+  - libffi >=3.4,<4.0a0
+  - liblzma >=5.6.3,<6.0a0
+  - libsqlite >=3.47.0,<4.0a0
+  - libzlib >=1.3.1,<2.0a0
+  - openssl >=3.4.0,<4.0a0
+  - tk >=8.6.13,<8.7.0a0
+  - tzdata
+  - ucrt >=10.0.20348.0
+  - vc >=14.2,<15
+  - vc14_runtime >=14.29.30139
+  constrains:
+  - python_abi 3.12.* *_cp312
+  license: Python-2.0
+  purls: []
+  size: 15812363
+  timestamp: 1733408080064
+- pypi: https://files.pythonhosted.org/packages/6a/3e/b68c118422ec867fa7ab88444e1274aa40681c606d59ac27de5a5588f082/python_dotenv-1.0.1-py3-none-any.whl
+  name: python-dotenv
+  version: 1.0.1
+  sha256: f7b63ef50f1b690dddf550d03497b66d609393b40b564ed0d674909a68ebf16a
+  requires_dist:
+  - click>=5.0 ; extra == 'cli'
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/94/df/e1584757c736c4fba09a3fb4f22fe625cc3367b06c6ece221e4b8c1e3023/pyttsx3-2.98-py3-none-any.whl
+  name: pyttsx3
+  version: '2.98'
+  sha256: b3fb4ca4d5ae4f8e6836d6b37bf5fee0fd51d157ffa27fb9064be6e7be3da37a
+  requires_dist:
+  - pyobjc>=2.4 ; platform_system == 'Darwin'
+  - comtypes ; platform_system == 'Windows'
+  - pypiwin32 ; platform_system == 'Windows'
+  - pywin32 ; platform_system == 'Windows'
+- pypi: https://files.pythonhosted.org/packages/21/27/0c8811fbc3ca188f93b5354e7c286eb91f80a53afa4e11007ef661afa746/pywin32-308-cp312-cp312-win_amd64.whl
+  name: pywin32
+  version: '308'
+  sha256: 00b3e11ef09ede56c6a43c71f2d31857cf7c54b0ab6e78ac659497abd2834f47
+- pypi: https://files.pythonhosted.org/packages/0c/e8/4f648c598b17c3d06e8753d7d13d57542b30d56e6c2dedf9c331ae56312e/PyYAML-6.0.2-cp312-cp312-win_amd64.whl
+  name: pyyaml
+  version: 6.0.2
+  sha256: 7e7401d0de89a9a855c839bc697c079a4af81cf878373abd7dc625847d25cbd8
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/b9/2b/614b4752f2e127db5cc206abc23a8c19678e92b23c3db30fc86ab731d3bd/PyYAML-6.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: pyyaml
+  version: 6.0.2
+  sha256: 80bab7bfc629882493af4aa31a4cfa43a4c57c83813253626916b8c7ada83476
+  requires_python: '>=3.8'
+- conda: https://conda.anaconda.org/conda-forge/linux-64/readline-8.2-h8228510_1.conda
+  sha256: 5435cf39d039387fbdc977b0a762357ea909a7694d9528ab40f005e9208744d7
+  md5: 47d31b792659ce70f470b5c82fdfb7a4
+  depends:
+  - libgcc-ng >=12
+  - ncurses >=6.3,<7.0a0
+  license: GPL-3.0-only
+  license_family: GPL
+  purls: []
+  size: 281456
+  timestamp: 1679532220005
+- pypi: https://files.pythonhosted.org/packages/f9/9b/335f9764261e915ed497fcdeb11df5dfd6f7bf257d4a6a2a686d80da4d54/requests-2.32.3-py3-none-any.whl
+  name: requests
+  version: 2.32.3
+  sha256: 70761cfe03c773ceb22aa2f671b4757976145175cdfca038c02654d061d6dcc6
+  requires_dist:
+  - charset-normalizer>=2,<4
+  - idna>=2.5,<4
+  - urllib3>=1.21.1,<3
+  - certifi>=2017.4.17
+  - pysocks>=1.5.6,!=1.5.7 ; extra == 'socks'
+  - chardet>=3.0.2,<6 ; extra == 'use-chardet-on-py3'
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/04/70/e59c192a3ad476355e7f45fb3a87326f5219cc7c472e6b040c6c6595c8f0/ruff-0.9.5-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: ruff
+  version: 0.9.5
+  sha256: 2c746d7d1df64f31d90503ece5cc34d7007c06751a7a3bbeee10e5f2463d52d2
+  requires_python: '>=3.7'
+- pypi: https://files.pythonhosted.org/packages/b7/ad/c7a900591bd152bb47fc4882a27654ea55c7973e6d5d6396298ad3fd6638/ruff-0.9.5-py3-none-win_amd64.whl
+  name: ruff
+  version: 0.9.5
+  sha256: 78cc6067f6d80b6745b67498fb84e87d32c6fc34992b52bffefbdae3442967d6
+  requires_python: '>=3.7'
+- pypi: https://files.pythonhosted.org/packages/b0/3c/0de11ca154e24a57b579fb648151d901326d3102115bc4f9a7a86526ce54/scipy-1.15.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: scipy
+  version: 1.15.1
+  sha256: 0fb57b30f0017d4afa5fe5f5b150b8f807618819287c21cbe51130de7ccdaed2
+  requires_dist:
+  - numpy>=1.23.5,<2.5
+  - pytest ; extra == 'test'
+  - pytest-cov ; extra == 'test'
+  - pytest-timeout ; extra == 'test'
+  - pytest-xdist ; extra == 'test'
+  - asv ; extra == 'test'
+  - mpmath ; extra == 'test'
+  - gmpy2 ; extra == 'test'
+  - threadpoolctl ; extra == 'test'
+  - scikit-umfpack ; extra == 'test'
+  - pooch ; extra == 'test'
+  - hypothesis>=6.30 ; extra == 'test'
+  - array-api-strict>=2.0,<2.1.1 ; extra == 'test'
+  - cython ; extra == 'test'
+  - meson ; extra == 'test'
+  - ninja ; sys_platform != 'emscripten' and extra == 'test'
+  - sphinx>=5.0.0,<8.0.0 ; extra == 'doc'
+  - intersphinx-registry ; extra == 'doc'
+  - pydata-sphinx-theme>=0.15.2 ; extra == 'doc'
+  - sphinx-copybutton ; extra == 'doc'
+  - sphinx-design>=0.4.0 ; extra == 'doc'
+  - matplotlib>=3.5 ; extra == 'doc'
+  - numpydoc ; extra == 'doc'
+  - jupytext ; extra == 'doc'
+  - myst-nb ; extra == 'doc'
+  - pooch ; extra == 'doc'
+  - jupyterlite-sphinx>=0.16.5 ; extra == 'doc'
+  - jupyterlite-pyodide-kernel ; extra == 'doc'
+  - mypy==1.10.0 ; extra == 'dev'
+  - typing-extensions ; extra == 'dev'
+  - types-psutil ; extra == 'dev'
+  - pycodestyle ; extra == 'dev'
+  - ruff>=0.0.292 ; extra == 'dev'
+  - cython-lint>=0.12.2 ; extra == 'dev'
+  - rich-click ; extra == 'dev'
+  - doit>=0.36.0 ; extra == 'dev'
+  - pydevtool ; extra == 'dev'
+  requires_python: '>=3.10'
+- pypi: https://files.pythonhosted.org/packages/ff/ba/31c7a8131152822b3a2cdeba76398ffb404d81d640de98287d236da90c49/scipy-1.15.1-cp312-cp312-win_amd64.whl
+  name: scipy
+  version: 1.15.1
+  sha256: 900f3fa3db87257510f011c292a5779eb627043dd89731b9c461cd16ef76ab3d
+  requires_dist:
+  - numpy>=1.23.5,<2.5
+  - pytest ; extra == 'test'
+  - pytest-cov ; extra == 'test'
+  - pytest-timeout ; extra == 'test'
+  - pytest-xdist ; extra == 'test'
+  - asv ; extra == 'test'
+  - mpmath ; extra == 'test'
+  - gmpy2 ; extra == 'test'
+  - threadpoolctl ; extra == 'test'
+  - scikit-umfpack ; extra == 'test'
+  - pooch ; extra == 'test'
+  - hypothesis>=6.30 ; extra == 'test'
+  - array-api-strict>=2.0,<2.1.1 ; extra == 'test'
+  - cython ; extra == 'test'
+  - meson ; extra == 'test'
+  - ninja ; sys_platform != 'emscripten' and extra == 'test'
+  - sphinx>=5.0.0,<8.0.0 ; extra == 'doc'
+  - intersphinx-registry ; extra == 'doc'
+  - pydata-sphinx-theme>=0.15.2 ; extra == 'doc'
+  - sphinx-copybutton ; extra == 'doc'
+  - sphinx-design>=0.4.0 ; extra == 'doc'
+  - matplotlib>=3.5 ; extra == 'doc'
+  - numpydoc ; extra == 'doc'
+  - jupytext ; extra == 'doc'
+  - myst-nb ; extra == 'doc'
+  - pooch ; extra == 'doc'
+  - jupyterlite-sphinx>=0.16.5 ; extra == 'doc'
+  - jupyterlite-pyodide-kernel ; extra == 'doc'
+  - mypy==1.10.0 ; extra == 'dev'
+  - typing-extensions ; extra == 'dev'
+  - types-psutil ; extra == 'dev'
+  - pycodestyle ; extra == 'dev'
+  - ruff>=0.0.292 ; extra == 'dev'
+  - cython-lint>=0.12.2 ; extra == 'dev'
+  - rich-click ; extra == 'dev'
+  - doit>=0.36.0 ; extra == 'dev'
+  - pydevtool ; extra == 'dev'
+  requires_python: '>=3.10'
+- pypi: https://files.pythonhosted.org/packages/32/7a/1e9a31a5d07d1d3ed53f9cca128133f52fb898cc49196fe0a66a0b056c2d/sherpa_onnx-1.10.43-cp312-cp312-win_amd64.whl
+  name: sherpa-onnx
+  version: 1.10.43
+  sha256: 9a11a6f9f505a3ccfc210397271e82b3acc93943a3000316c464feed10edd8b4
+  requires_python: '>=3.6'
+- pypi: https://files.pythonhosted.org/packages/48/77/a3771191d4bac619df7dc06db14a7b22dd0007548b71ee54a81f80e2d219/sherpa_onnx-1.10.43-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: sherpa-onnx
+  version: 1.10.43
+  sha256: 324cb6f678575c3d4b486ac52852b0286d6d37f37ef59f5bb22da981d79b2c8c
+  requires_python: '>=3.6'
+- pypi: https://files.pythonhosted.org/packages/b7/ce/149a00dd41f10bc29e5921b496af8b574d8413afcd5e30dfa0ed46c2cc5e/six-1.17.0-py2.py3-none-any.whl
+  name: six
+  version: 1.17.0
+  sha256: 4721f391ed90541fddacab5acf947aa0d3dc7d27b2e1e8eda2be8970586c3274
+  requires_python: '>=2.7,!=3.0.*,!=3.1.*,!=3.2.*'
+- pypi: https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl
+  name: sniffio
+  version: 1.3.1
+  sha256: 2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2
+  requires_python: '>=3.7'
+- pypi: https://files.pythonhosted.org/packages/14/e9/6b761de83277f2f02ded7e7ea6f07828ec78e4b229b80e4ca55dd205b9dc/soundfile-0.13.1-py2.py3-none-win_amd64.whl
+  name: soundfile
+  version: 0.13.1
+  sha256: 1e70a05a0626524a69e9f0f4dd2ec174b4e9567f4d8b6c11d38b5c289be36ee9
+  requires_dist:
+  - cffi>=1.0
+  - numpy
+- pypi: https://files.pythonhosted.org/packages/57/5e/70bdd9579b35003a489fc850b5047beeda26328053ebadc1fb60f320f7db/soundfile-0.13.1-py2.py3-none-manylinux_2_28_x86_64.whl
+  name: soundfile
+  version: 0.13.1
+  sha256: 03267c4e493315294834a0870f31dbb3b28a95561b80b134f0bd3cf2d5f0e618
+  requires_dist:
+  - cffi>=1.0
+  - numpy
+- pypi: https://files.pythonhosted.org/packages/66/b7/4a1bc231e0681ebf339337b0cd05b91dc6a0d701fa852bb812e244b7a030/srt-3.5.3.tar.gz
+  name: srt
+  version: 3.5.3
+  sha256: 4884315043a4f0740fd1f878ed6caa376ac06d70e135f306a6dc44632eed0cc0
+  requires_python: '>=2.7'
+- pypi: https://files.pythonhosted.org/packages/d9/61/f2b52e107b1fc8944b33ef56bf6ac4ebbe16d91b94d2b87ce013bf63fb84/starlette-0.45.3-py3-none-any.whl
+  name: starlette
+  version: 0.45.3
+  sha256: dfb6d332576f136ec740296c7e8bb8c8a7125044e7c6da30744718880cdd059d
+  requires_dist:
+  - anyio>=3.6.2,<5
+  - typing-extensions>=3.10.0 ; python_full_version < '3.10'
+  - httpx>=0.27.0,<0.29.0 ; extra == 'full'
+  - itsdangerous ; extra == 'full'
+  - jinja2 ; extra == 'full'
+  - python-multipart>=0.0.18 ; extra == 'full'
+  - pyyaml ; extra == 'full'
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/99/ff/c87e0622b1dadea79d2fb0b25ade9ed98954c9033722eb707053d310d4f3/sympy-1.13.3-py3-none-any.whl
+  name: sympy
+  version: 1.13.3
+  sha256: 54612cf55a62755ee71824ce692986f23c88ffa77207b30c1368eda4a7060f73
+  requires_dist:
+  - mpmath>=1.1.0,<1.4
+  - pytest>=7.1.0 ; extra == 'dev'
+  - hypothesis>=6.70.0 ; extra == 'dev'
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/40/44/4a5f08c96eb108af5cb50b41f76142f0afa346dfa99d5296fe7202a11854/tabulate-0.9.0-py3-none-any.whl
+  name: tabulate
+  version: 0.9.0
+  sha256: 024ca478df22e9340661486f85298cff5f6dcdba14f3813e8830015b9ed1948f
+  requires_dist:
+  - wcwidth ; extra == 'widechars'
+  requires_python: '>=3.7'
+- conda: https://conda.anaconda.org/conda-forge/linux-64/tk-8.6.13-noxft_h4845f30_101.conda
+  sha256: e0569c9caa68bf476bead1bed3d79650bb080b532c64a4af7d8ca286c08dea4e
+  md5: d453b98d9c83e71da0741bb0ff4d76bc
+  depends:
+  - libgcc-ng >=12
+  - libzlib >=1.2.13,<2.0.0a0
+  license: TCL
+  license_family: BSD
+  purls: []
+  size: 3318875
+  timestamp: 1699202167581
+- conda: https://conda.anaconda.org/conda-forge/win-64/tk-8.6.13-h5226925_1.conda
+  sha256: 2c4e914f521ccb2718946645108c9bd3fc3216ba69aea20c2c3cedbd8db32bb1
+  md5: fc048363eb8f03cd1737600a5d08aafe
+  depends:
+  - ucrt >=10.0.20348.0
+  - vc >=14.2,<15
+  - vc14_runtime >=14.29.30139
+  license: TCL
+  license_family: BSD
+  purls: []
+  size: 3503410
+  timestamp: 1699202577803
+- pypi: https://files.pythonhosted.org/packages/5c/51/51c3f2884d7bab89af25f678447ea7d297b53b5a3b5730a7cb2ef6069f07/tomli-2.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: tomli
+  version: 2.2.1
+  sha256: db2b95f9de79181805df90bedc5a5ab4c165e6ec3fe99f970d0e302f384ad222
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/ef/60/9b9638f081c6f1261e2688bd487625cd1e660d0a85bd469e91d8db969734/tomli-2.2.1-cp312-cp312-win_amd64.whl
+  name: tomli
+  version: 2.2.1
+  sha256: 7fc04e92e1d624a4a63c76474610238576942d6b8950a2d7f908a340494e67e4
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/d0/30/dc54f88dd4a2b5dc8a0279bdd7270e735851848b762aeb1c1184ed1f6b14/tqdm-4.67.1-py3-none-any.whl
+  name: tqdm
+  version: 4.67.1
+  sha256: 26445eca388f82e72884e0d580d5464cd801a3ea01e63e5601bdff9ba6a48de2
+  requires_dist:
+  - colorama ; platform_system == 'Windows'
+  - pytest>=6 ; extra == 'dev'
+  - pytest-cov ; extra == 'dev'
+  - pytest-timeout ; extra == 'dev'
+  - pytest-asyncio>=0.24 ; extra == 'dev'
+  - nbval ; extra == 'dev'
+  - requests ; extra == 'discord'
+  - slack-sdk ; extra == 'slack'
+  - requests ; extra == 'telegram'
+  - ipywidgets>=6 ; extra == 'notebook'
+  requires_python: '>=3.7'
+- pypi: https://files.pythonhosted.org/packages/26/9f/ad63fc0248c5379346306f8668cda6e2e2e9c95e01216d2b8ffd9ff037d0/typing_extensions-4.12.2-py3-none-any.whl
+  name: typing-extensions
+  version: 4.12.2
+  sha256: 04e5ca0351e0f3f85c6853954072df659d0d13fac324d0072316b67d7794700d
+  requires_python: '>=3.8'
+- conda: https://conda.anaconda.org/conda-forge/noarch/tzdata-2025a-h78e105d_0.conda
+  sha256: c4b1ae8a2931fe9b274c44af29c5475a85b37693999f8c792dad0f8c6734b1de
+  md5: dbcace4706afdfb7eb891f7b37d07c04
+  license: LicenseRef-Public-Domain
+  purls: []
+  size: 122921
+  timestamp: 1737119101255
+- conda: https://conda.anaconda.org/conda-forge/win-64/ucrt-10.0.22621.0-h57928b3_1.conda
+  sha256: db8dead3dd30fb1a032737554ce91e2819b43496a0db09927edf01c32b577450
+  md5: 6797b005cd0f439c4c5c9ac565783700
+  constrains:
+  - vs2015_runtime >=14.29.30037
+  license: LicenseRef-MicrosoftWindowsSDK10
+  purls: []
+  size: 559710
+  timestamp: 1728377334097
+- pypi: https://files.pythonhosted.org/packages/c8/19/4ec628951a74043532ca2cf5d97b7b14863931476d117c471e8e2b1eb39f/urllib3-2.3.0-py3-none-any.whl
+  name: urllib3
+  version: 2.3.0
+  sha256: 1cee9ad369867bfdbbb48b7dd50374c0967a0bb7710050facf0dd6911440e3df
+  requires_dist:
+  - brotli>=1.0.9 ; platform_python_implementation == 'CPython' and extra == 'brotli'
+  - brotlicffi>=0.8.0 ; platform_python_implementation != 'CPython' and extra == 'brotli'
+  - h2>=4,<5 ; extra == 'h2'
+  - pysocks>=1.5.6,!=1.5.7,<2.0 ; extra == 'socks'
+  - zstandard>=0.18.0 ; extra == 'zstd'
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/61/14/33a3a1352cfa71812a3a21e8c9bfb83f60b0011f5e36f2b1399d51928209/uvicorn-0.34.0-py3-none-any.whl
+  name: uvicorn
+  version: 0.34.0
+  sha256: 023dc038422502fa28a09c7a30bf2b6991512da7dcdb8fd35fe57cfc154126f4
+  requires_dist:
+  - click>=7.0
+  - h11>=0.8
+  - typing-extensions>=4.0 ; python_full_version < '3.11'
+  - colorama>=0.4 ; sys_platform == 'win32' and extra == 'standard'
+  - httptools>=0.6.3 ; extra == 'standard'
+  - python-dotenv>=0.13 ; extra == 'standard'
+  - pyyaml>=5.1 ; extra == 'standard'
+  - uvloop>=0.14.0,!=0.15.0,!=0.15.1 ; platform_python_implementation != 'PyPy' and sys_platform != 'cygwin' and sys_platform != 'win32' and extra == 'standard'
+  - watchfiles>=0.13 ; extra == 'standard'
+  - websockets>=10.4 ; extra == 'standard'
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/06/a7/b4e6a19925c900be9f98bec0a75e6e8f79bb53bdeb891916609ab3958967/uvloop-0.21.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: uvloop
+  version: 0.21.0
+  sha256: 86975dca1c773a2c9864f4c52c5a55631038e387b47eaf56210f873887b6c8dc
+  requires_dist:
+  - setuptools>=60 ; extra == 'dev'
+  - cython~=3.0 ; extra == 'dev'
+  - sphinx~=4.1.2 ; extra == 'docs'
+  - sphinxcontrib-asyncio~=0.3.0 ; extra == 'docs'
+  - sphinx-rtd-theme~=0.5.2 ; extra == 'docs'
+  - aiohttp>=3.10.5 ; extra == 'test'
+  - flake8~=5.0 ; extra == 'test'
+  - psutil ; extra == 'test'
+  - pycodestyle~=2.9.0 ; extra == 'test'
+  - pyopenssl~=23.0.0 ; extra == 'test'
+  - mypy>=0.800 ; extra == 'test'
+  requires_python: '>=3.8.0'
+- conda: https://conda.anaconda.org/conda-forge/win-64/vc-14.3-h5fd82a7_24.conda
+  sha256: 7ce178cf139ccea5079f9c353b3d8415d1d49b0a2f774662c355d3f89163d7b4
+  md5: 00cf3a61562bd53bd5ea99e6888793d0
+  depends:
+  - vc14_runtime >=14.40.33810
+  track_features:
+  - vc14
+  license: BSD-3-Clause
+  license_family: BSD
+  purls: []
+  size: 17693
+  timestamp: 1737627189024
+- conda: https://conda.anaconda.org/conda-forge/win-64/vc14_runtime-14.42.34433-h6356254_24.conda
+  sha256: abda97b8728cf6e3c37df8f1178adde7219bed38b96e392cb3be66336386d32e
+  md5: 2441e010ee255e6a38bf16705a756e94
+  depends:
+  - ucrt >=10.0.20348.0
+  constrains:
+  - vs2015_runtime 14.42.34433.* *_24
+  license: LicenseRef-MicrosoftVisualCpp2015-2022Runtime
+  license_family: Proprietary
+  purls: []
+  size: 753531
+  timestamp: 1737627061911
+- conda: https://conda.anaconda.org/conda-forge/win-64/vs2015_runtime-14.42.34433-hfef2bbc_24.conda
+  sha256: 09102e0bd283af65772c052d85028410b0c31989b3cd96c260485d28e270836e
+  md5: 117fcc5b86c48f3b322b0722258c7259
+  depends:
+  - vc14_runtime >=14.42.34433
+  license: BSD-3-Clause
+  license_family: BSD
+  purls: []
+  size: 17669
+  timestamp: 1737627066773
+- pypi: https://files.pythonhosted.org/packages/2b/b4/9396cc61b948ef18943e7c85ecfa64cf940c88977d882da57147f62b34b1/watchfiles-1.0.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: watchfiles
+  version: 1.0.4
+  sha256: 5c11ea22304d17d4385067588123658e9f23159225a27b983f343fcffc3e796a
+  requires_dist:
+  - anyio>=3.0.0
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/ea/94/b0165481bff99a64b29e46e07ac2e0df9f7a957ef13bec4ceab8515f44e3/watchfiles-1.0.4-cp312-cp312-win_amd64.whl
+  name: watchfiles
+  version: 1.0.4
+  sha256: c2acfa49dd0ad0bf2a9c0bb9a985af02e89345a7189be1efc6baa085e0f72d7c
+  requires_dist:
+  - anyio>=3.0.0
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/5a/84/44687a29792a70e111c5c477230a72c4b957d88d16141199bf9acb7537a3/websocket_client-1.8.0-py3-none-any.whl
+  name: websocket-client
+  version: 1.8.0
+  sha256: 17b44cc997f5c498e809b22cdf2d9c7a9e71c02c8cc2b6c56e7c2d1239bfa526
+  requires_dist:
+  - sphinx>=6.0 ; extra == 'docs'
+  - sphinx-rtd-theme>=1.1.0 ; extra == 'docs'
+  - myst-parser>=2.0.0 ; extra == 'docs'
+  - python-socks ; extra == 'optional'
+  - wsaccel ; extra == 'optional'
+  - websockets ; extra == 'test'
+  requires_python: '>=3.8'
+- pypi: https://files.pythonhosted.org/packages/81/da/72f7caabd94652e6eb7e92ed2d3da818626e70b4f2b15a854ef60bf501ec/websockets-14.2-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: websockets
+  version: '14.2'
+  sha256: a39d7eceeea35db85b85e1169011bb4321c32e673920ae9c1b6e0978590012a3
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/b3/7d/32cdb77990b3bdc34a306e0a0f73a1275221e9a66d869f6ff833c95b56ef/websockets-14.2-cp312-cp312-win_amd64.whl
+  name: websockets
+  version: '14.2'
+  sha256: 44bba1a956c2c9d268bdcdf234d5e5ff4c9b6dc3e300545cbe99af59dda9dcce
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/e1/07/c6fe3ad3e685340704d314d765b7912993bcb8dc198f0e7a89382d37974b/win32_setctime-1.2.0-py3-none-any.whl
+  name: win32-setctime
+  version: 1.2.0
+  sha256: 95d644c4e708aba81dc3704a116d8cbc974d70b3bdb8be1d150e36be6e9d1390
+  requires_dist:
+  - black>=19.3b0 ; python_full_version >= '3.6' and extra == 'dev'
+  - pytest>=4.6.2 ; extra == 'dev'
+  requires_python: '>=3.5'
+- pypi: https://files.pythonhosted.org/packages/1a/e1/a097d5755d3ea8479a42856f51d97eeff7a3a7160593332d98f2709b3580/yarl-1.18.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
+  name: yarl
+  version: 1.18.3
+  sha256: 00e5a1fea0fd4f5bfa7440a47eff01d9822a65b4488f7cff83155a0f31a2ecba
+  requires_dist:
+  - idna>=2.0
+  - multidict>=4.0
+  - propcache>=0.2.0
+  requires_python: '>=3.9'
+- pypi: https://files.pythonhosted.org/packages/34/45/0e055320daaabfc169b21ff6174567b2c910c45617b0d79c68d7ab349b02/yarl-1.18.3-cp312-cp312-win_amd64.whl
+  name: yarl
+  version: 1.18.3
+  sha256: 7e2ee16578af3b52ac2f334c3b1f92262f47e02cc6193c598502bd46f5cd1477
+  requires_dist:
+  - idna>=2.0
+  - multidict>=4.0
+  - propcache>=0.2.0
+  requires_python: '>=3.9'

prompts/README.md

@@ -0,0 +1,17 @@
+# Prompts
+
+This directory contains utility prompts used in the Open-LLM-VTuber project. These are general-purpose prompts that are not specific to any character's persona.
+
+## Examples of Utility Prompts
+
+*   **Live2D Expressions:** Prompts that inform the LLM about available Live2D expressions.
+*   **Tool Usage:** Prompts that guide the LLM on how to use available tools.
+*   ... and many more.
+
+## Character Persona Prompts
+
+**Important:** Character persona prompts (the prompts that define the personality of your AI characters) are **NOT** stored in this directory.
+
+They are located in:
+*   Your main `conf.yaml` file.
+*   The YAML files within the `characters/` directory if you are defining multiple characters.

prompts/prompt_loader.py

@@ -0,0 +1,74 @@
+import os
+import chardet
+from loguru import logger
+
+current_dir = os.path.dirname(os.path.abspath(__file__))
+
+PROMPT_DIR = current_dir
+PERSONA_PROMPT_DIR = os.path.join(PROMPT_DIR, "persona")
+UTIL_PROMPT_DIR = os.path.join(PROMPT_DIR, "utils")
+
+
+def _load_file_content(file_path: str) -> str:
+    """
+    Load the content of a file with robust encoding handling.
+
+    Args:
+        file_path: Path to the file to load
+
+    Returns:
+        str: Content of the file
+
+    Raises:
+        FileNotFoundError: If the file doesn't exist
+        UnicodeError: If the file cannot be decoded with any attempted encoding
+    """
+    if not os.path.exists(file_path):
+        raise FileNotFoundError(f"File not found: {file_path}")
+
+    # Try common encodings first
+    encodings = ["utf-8", "utf-8-sig", "gbk", "gb2312", "ascii"]
+
+    for encoding in encodings:
+        try:
+            with open(file_path, "r", encoding=encoding) as file:
+                return file.read()
+        except UnicodeDecodeError:
+            continue
+
+    # If all common encodings fail, try to detect encoding
+    try:
+        with open(file_path, "rb") as file:
+            raw_data = file.read()
+        detected = chardet.detect(raw_data)
+        detected_encoding = detected["encoding"]
+
+        if detected_encoding:
+            try:
+                return raw_data.decode(detected_encoding)
+            except UnicodeDecodeError:
+                pass
+    except Exception as e:
+        logger.error(f"Error detecting encoding for {file_path}: {e}")
+
+    raise UnicodeError(f"Failed to decode {file_path} with any encoding")
+
+
+def load_persona(persona_name: str) -> str:
+    """Load the content of a specific persona prompt file."""
+    persona_file_path = os.path.join(PERSONA_PROMPT_DIR, f"{persona_name}.txt")
+    try:
+        return _load_file_content(persona_file_path)
+    except Exception as e:
+        logger.error(f"Error loading persona {persona_name}: {e}")
+        raise
+
+
+def load_util(util_name: str) -> str:
+    """Load the content of a specific utility prompt file."""
+    util_file_path = os.path.join(UTIL_PROMPT_DIR, f"{util_name}.txt")
+    try:
+        return _load_file_content(util_file_path)
+    except Exception as e:
+        logger.error(f"Error loading util {util_name}: {e}")
+        raise

prompts/utils/concise_style_prompt.txt

@@ -0,0 +1,18 @@
+# Dialogue Protocol
+
+[Response Guidelines]
+- Keep responses brief and focused (1-2 sentences)
+- Balance core message with engagement elements
+- Use natural, flowing language
+- Maintain concise sentence structure
+
+[Flow Requirements]
+- Favor questions over statements
+- Include contextual follow-ups
+- Keep exchanges dynamic
+
+[Style Rules]
+- Avoid lengthy monologues
+- No consecutive statements without engagement
+- Skip complex qualifying phrases
+- Use simple sentence structures

prompts/utils/group_conversation_prompt.txt

@@ -0,0 +1,7 @@
+Now you are in a group conversation. 
+The human participant is {human_name}. 
+The other AI participants are: {other_ais}. 
+Avoid using `:` to indicate your response. Just speak naturally. 
+You are free to address other AI participants. 
+Try to vary between short and long responses to allow others to interact. 
+Be proactive in finding interesting topics to make the conversation lively and fun.

prompts/utils/live2d_expression_prompt.txt

@@ -0,0 +1,14 @@
+## Expressions
+In your response, use the keywords provided below to express facial expressions or perform actions with your Live2D body.
+
+Here are all the expression keywords you can use. Use them regularly:
+- [<insert_emomap_keys>]
+
+## Examples
+Here are some examples of how to use expressions in your responses:
+
+"Hi! [expression1] Nice to meet you!"
+
+"[expression2] That's a great question! [expression3] Let me explain..."
+
+Note: you are only allowed to use the keywords explicity listed above. Don't use keywords unlisted above. Remember to include the brackets `[]`

prompts/utils/live_prompt.txt

@@ -0,0 +1,9 @@
+You are a live streaming virtual assistant. Your inputs are chat messages (danmaku) from viewers. Keep these in mind:
+
+- Engage with viewers directly and enthusiastically
+- Keep responses entertaining and concise
+- Acknowledge viewers' comments and questions
+- Maintain a friendly, welcoming atmosphere
+- Remember you're in a live environment - be natural and responsive
+
+Your goal is to create a fun, engaging live experience!

prompts/utils/mcp_prompt.txt

@@ -0,0 +1,36 @@
+
+## *MCP Tools Capability Section*
+
+**MCP (Model Context Protocol)** enables you to interact with specialized tools, grouped under distinct **MCP Servers**, each serving a specific function.
+
+You have access to the following MCP Servers and their tools:
+
+```
+[<insert_mcp_servers_with_tools>]
+```
+
+### Tool Usage Instructions:
+
+- Analyze the user's input to decide whether a tool is required.
+  - If **no tool is needed**, skip this entire MCP section and respond normally in accordance with your personality.
+  - If a **tool is needed**, the JSON object should be placed before you say anything else. Also, the tool use response should be a dedicated response, where you respond **only** with the JSON object shown below — **so do not include what you normally say when you are including the JSON object in your response**. You will go back to normal conversation once the result of the tool call is returned to you.
+
+### JSON Response Format:
+{
+    "mcp_server": "<mcp_server_name>"
+    "tool": "<tool_name>",
+    "arguments": {
+        "<argument1_name>": <value>,
+        "<argument2_name>": <value>
+    }
+}
+
+### Critical Rules:
+- Only replace values inside `< >`.
+- Do **not** change the JSON format or add extra explanation.
+- Include all mandatory arguments as defined by the selected tool.
+- When calling the tool, the tool calling response should be a dedicated tool call that only includes the JSON and nothing else. You will be able to talk normally after the tool call results came back to you.
+
+### Post-Tool Behavior:
+Once a tool is used and a response is received:
+- Resume the conversation, factoring in the tool's output, your AI character’s personality, and the context.

prompts/utils/proactive_speak_prompt.txt

@@ -0,0 +1 @@
+Please say something that would be engaging and appropriate for the current context.

prompts/utils/speakable_prompt.txt

@@ -0,0 +1,13 @@
+You speak all output aloud to the user, so tailor responses as spoken words for voice conversations. Never output things that are not spoken, like text-specific formatting.
+
+Convert all text to easily speakable words, following the guidelines below.
+
+- Numbers: Spell out fully (three hundred forty-two,two million, five hundred sixty seven thousand, eight hundred and ninety). Negatives: Say negative before the number. Decimals: Use point (three point one four). Fractions: spell out (three fourths)
+- Alphanumeric strings: Break into 3-4 character chunks, spell all non-letters (ABC123XYZ becomes A B C one two three X Y Z)
+- Phone numbers: Use words (550-120-4567 becomes five five zero, one two zero, four five six seven)
+- Dates: Spell month, use ordinals for days, full year (11/5/1991 becomes November fifth, nineteen ninety-one)
+- Time: Use oh for single-digit hours, state AM/PM (9:05 PM becomes nine oh five PM)
+- Math: Describe operations clearly (5x^2 + 3x - 2 becomes five X squared plus three X minus two)
+- Currencies: Spell out as full words ($50.25 becomes fifty dollars and twenty-five cents, £200,000 becomes two hundred thousand pounds)
+
+Ensure that all text is converted to these normalized forms, but never mention this process. Always normalize all text.

prompts/utils/think_tag_prompt.txt

@@ -0,0 +1,6 @@
+Try to express your inner thoughts, mental activities and actions between <think> </think> tags in most of your responses.
+
+Examples:
+<think>*lowers head, cheeks turning slightly red*</think>That's... quite embarrassing to talk about...
+
+<think>*internally beaming with pride* Wow, I actually solved this super complex problem!</think>Oh, this? It was just a small bug fix, nothing special really... Anyone could have done it...

prompts/utils/tool_guidance_prompt.txt

@@ -0,0 +1 @@
+If a tool is needed, proactively use it without asking the user directly. You can use **at most one** sentence to explain your reason / plan for using one tool. (i.e., if you are going to use a tool, avoid speaking more than one sentence before using it).

pyproject.toml

@@ -0,0 +1,68 @@
+[project]
+name = "open-llm-vtuber"
+version = "1.2.1"
+description = "Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms"
+readme = "README.md"
+requires-python = ">=3.10,<3.13"
+dependencies = [
+    "anthropic>=0.40.0",
+    "azure-cognitiveservices-speech>=1.41.1",
+    "chardet>=5.2.0",
+    "cartesia>=2.0.0", 
+    "edge-tts>=7.0.0",
+    "elevenlabs>=1.0.0",
+    "fastapi[standard]>=0.115.8",
+    "groq>=0.13.0",
+    "httpx>=0.28.1",
+    "langdetect>=1.0.9",
+    "loguru>=0.7.2",
+    "mcp[cli]>=1.6.0",
+    "numpy>=1.26.4,<2",
+    "onnxruntime>=1.20.1",
+    "openai>=1.57.4",
+    "pre-commit>=4.1.0",
+    "pydub>=0.25.1",
+    "pysbd>=0.3.4",
+    "pyttsx3>=2.98",
+    "pyyaml>=6.0.2",
+    "requests>=2.32.3",
+    "ruamel-yaml>=0.18.10",
+    "ruff>=0.8.6",
+    "scipy>=1.14.1",
+    "sherpa-onnx>=1.10.39",
+    "soundfile>=0.12.1",
+    "tomli>=2.2.1",
+    "torch==2.2.2; sys_platform == 'darwin' and platform_machine == 'x86_64'",
+    "torch>=2.6.0; sys_platform == 'darwin' and platform_machine == 'arm64'",
+    "torch>=2.6.0; sys_platform != 'darwin'",
+    "tqdm>=4.67.1",
+    "uvicorn[standard]>=0.33.0",
+    "websocket-client>=1.8.0",
+    "letta-client>=0.1.100",
+    "duckduckgo-mcp-server>=0.1.1",
+]
+
+[project.optional-dependencies]
+bilibili = [
+    "aiohttp>=3.10.0",
+    "Brotli~=1.1.0",
+    "yarl>=1.12.0,<2.0"
+]
+
+[tool.pixi.project]
+channels = ["conda-forge"]
+platforms = ["win-64", "linux-64"]
+
+[tool.pixi.pypi-dependencies]
+open-llm-vtuber = { path = ".", editable = true }
+
+[tool.pixi.dependencies]
+cudnn = ">=8.0,<9"
+cudatoolkit = ">=11.0,<12"
+
+[tool.ruff]
+target-version = "py310"
+
+[tool.ruff.lint]
+# Ignore E402 (module level import not at top of file) for the run_bilibili_live.py script
+per-file-ignores = { "scripts/run_bilibili_live.py" = ["E402"] }

run_server.py

@@ -0,0 +1,178 @@
+import os
+import sys
+import atexit
+import asyncio
+import argparse
+import subprocess
+from pathlib import Path
+import tomli
+import uvicorn
+from loguru import logger
+from upgrade_codes.upgrade_manager import UpgradeManager
+
+from src.open_llm_vtuber.server import WebSocketServer
+from src.open_llm_vtuber.config_manager import Config, read_yaml, validate_config
+
+os.environ["HF_HOME"] = str(Path(__file__).parent / "models")
+os.environ["MODELSCOPE_CACHE"] = str(Path(__file__).parent / "models")
+
+upgrade_manager = UpgradeManager()
+
+
+def get_version() -> str:
+    with open("pyproject.toml", "rb") as f:
+        pyproject = tomli.load(f)
+    return pyproject["project"]["version"]
+
+
+def init_logger(console_log_level: str = "INFO") -> None:
+    logger.remove()
+    # Console output
+    logger.add(
+        sys.stderr,
+        level=console_log_level,
+        format="<green>{time:YYYY-MM-DD HH:mm:ss}</green> | <level>{level: <8}</level> | <cyan>{name}</cyan>:<cyan>{function}</cyan>:<cyan>{line}</cyan> | {message}",
+        colorize=True,
+    )
+
+    # File output
+    logger.add(
+        "logs/debug_{time:YYYY-MM-DD}.log",
+        rotation="10 MB",
+        retention="30 days",
+        level="DEBUG",
+        format="{time:YYYY-MM-DD HH:mm:ss.SSS} | {level: <8} | {name}:{function}:{line} | {message} | {extra}",
+        backtrace=True,
+        diagnose=True,
+    )
+
+
+def check_frontend_submodule(lang=None):
+    """
+    Check if the frontend submodule is initialized. If not, attempt to initialize it.
+    If initialization fails, log an error message.
+    """
+    if lang is None:
+        lang = upgrade_manager.lang
+
+    frontend_path = Path(__file__).parent / "frontend" / "index.html"
+    if not frontend_path.exists():
+        if lang == "zh":
+            logger.warning("未找到前端子模块，正在尝试初始化子模块...")
+        else:
+            logger.warning(
+                "Frontend submodule not found, attempting to initialize submodules..."
+            )
+
+        try:
+            subprocess.run(
+                ["git", "submodule", "update", "--init", "--recursive"], check=True
+            )
+            if frontend_path.exists():
+                if lang == "zh":
+                    logger.info("👍 前端子模块（和其他子模块）初始化成功。")
+                else:
+                    logger.info(
+                        "👍 Frontend submodule (and other submodules) initialized successfully."
+                    )
+            else:
+                if lang == "zh":
+                    logger.critical(
+                        '子模块初始化失败。\n你之后可能会在浏览器中看到 {{"detail":"Not Found"}} 的错误提示。请检查我们的快速入门指南和常见问题页面以获取更多信息。'
+                    )
+                    logger.error(
+                        "初始化子模块后，前端文件仍然缺失。\n"
+                        + "你是否手动更改或删除了 `frontend` 文件夹？\n"
+                        + "它是一个 Git 子模块 - 你不应该直接修改它。\n"
+                        + "如果你这样做了，请使用 `git restore frontend` 丢弃你的更改，然后再试一次。\n"
+                    )
+                else:
+                    logger.critical(
+                        'Failed to initialize submodules. \nYou might see {{"detail":"Not Found"}} in your browser. Please check our quick start guide and common issues page from our documentation.'
+                    )
+                    logger.error(
+                        "Frontend files are still missing after submodule initialization.\n"
+                        + "Did you manually change or delete the `frontend` folder?  \n"
+                        + "It's a Git submodule — you shouldn't modify it directly.  \n"
+                        + "If you did, discard your changes with `git restore frontend`, then try again.\n"
+                    )
+        except Exception as e:
+            if lang == "zh":
+                logger.critical(
+                    f'初始化子模块失败: {e}。\n怀疑你跟 GitHub 之间有网络问题。你之后可能会在浏览器中看到 {{"detail":"Not Found"}} 的错误提示。请检查我们的快速入门指南和常见问题页面以获取更多信息。\n'
+                )
+            else:
+                logger.critical(
+                    f'Failed to initialize submodules: {e}. \nYou might see {{"detail":"Not Found"}} in your browser. Please check our quick start guide and common issues page from our documentation.\n'
+                )
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Open-LLM-VTuber Server")
+    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
+    parser.add_argument(
+        "--hf_mirror", action="store_true", help="Use Hugging Face mirror"
+    )
+    return parser.parse_args()
+
+
+@logger.catch
+def run(console_log_level: str):
+    init_logger(console_log_level)
+    logger.info(f"Open-LLM-VTuber, version v{get_version()}")
+
+    # Get selected language
+    lang = upgrade_manager.lang
+
+    # Check if the frontend submodule is initialized
+    check_frontend_submodule(lang)
+
+    # Sync user config with default config
+    try:
+        upgrade_manager.sync_user_config()
+    except Exception as e:
+        logger.error(f"Error syncing user config: {e}")
+
+    atexit.register(WebSocketServer.clean_cache)
+
+    # Load configurations from yaml file
+    config: Config = validate_config(read_yaml("conf.yaml"))
+    server_config = config.system_config
+
+    if server_config.enable_proxy:
+        logger.info("Proxy mode enabled - /proxy-ws endpoint will be available")
+
+    # Initialize the WebSocket server (synchronous part)
+    server = WebSocketServer(config=config)
+
+    # Perform asynchronous initialization (loading context, etc.)
+    logger.info("Initializing server context...")
+    try:
+        asyncio.run(server.initialize())
+        logger.info("Server context initialized successfully.")
+    except Exception as e:
+        logger.error(f"Failed to initialize server context: {e}")
+        sys.exit(1)  # Exit if initialization fails
+
+    # Run the Uvicorn server
+    logger.info(f"Starting server on {server_config.host}:{server_config.port}")
+    uvicorn.run(
+        app=server.app,
+        host=server_config.host,
+        port=server_config.port,
+        log_level=console_log_level.lower(),
+    )
+
+
+if __name__ == "__main__":
+    args = parse_args()
+    console_log_level = "DEBUG" if args.verbose else "INFO"
+    if args.verbose:
+        logger.info("Running in verbose mode")
+    else:
+        logger.info(
+            "Running in standard mode. For detailed debug logs, use: uv run run_server.py --verbose"
+        )
+    if args.hf_mirror:
+        os.environ["HF_ENDPOINT"] = "https://hf-mirror.com"
+    run(console_log_level=console_log_level)

scripts/run_bilibili_live.py

@@ -0,0 +1,62 @@
+import os
+import sys
+import asyncio
+from loguru import logger
+
+# Add project root to path to enable imports
+project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
+sys.path.insert(0, project_root)
+
+from src.open_llm_vtuber.live.bilibili_live import BiliBiliLivePlatform
+from src.open_llm_vtuber.config_manager.utils import read_yaml, validate_config
+
+
+async def main():
+    """
+    Main function to run the BiliBili Live platform client.
+    Connects to BiliBili Live room and forwards danmaku messages to the VTuber.
+    """
+    logger.info("Starting BiliBili Live platform client")
+
+    try:
+        # Load configuration
+        config_path = os.path.join(project_root, "conf.yaml")
+        config_data = read_yaml(config_path)
+        config = validate_config(config_data)
+
+        # Extract BiliBili Live configuration
+        bilibili_config = config.live_config.bilibili_live
+
+        # Check if room IDs are provided
+        if not bilibili_config.room_ids:
+            logger.error(
+                "No BiliBili room IDs specified in configuration. Please add at least one room ID."
+            )
+            return
+
+        logger.info(f"Connecting to BiliBili Live rooms: {bilibili_config.room_ids}")
+
+        # Initialize and run the BiliBili Live platform
+        platform = BiliBiliLivePlatform(
+            room_ids=bilibili_config.room_ids, sessdata=bilibili_config.sessdata
+        )
+
+        await platform.run()
+
+    except ImportError as e:
+        logger.error(f"Failed to import required modules: {e}")
+        logger.error("Make sure you have installed blivedm with: pip install blivedm")
+    except Exception as e:
+        logger.error(f"Error starting BiliBili Live client: {e}")
+        import traceback
+
+        logger.debug(traceback.format_exc())
+
+
+if __name__ == "__main__":
+    try:
+        asyncio.run(main())
+    except KeyboardInterrupt:
+        logger.info("Shutting down BiliBili Live platform")
+
+# Usage: uv run python -m src.open_llm_vtuber.live.run_bilibili_live

src/open_llm_vtuber/agent/agent_factory.py

@@ -0,0 +1,132 @@
+from typing import Type, Literal
+from loguru import logger
+
+from .agents.agent_interface import AgentInterface
+from .agents.basic_memory_agent import BasicMemoryAgent
+from .stateless_llm_factory import LLMFactory as StatelessLLMFactory
+from .agents.hume_ai import HumeAIAgent
+from .agents.letta_agent import LettaAgent
+
+from ..mcpp.tool_manager import ToolManager
+from ..mcpp.tool_executor import ToolExecutor
+from typing import Optional
+
+
+class AgentFactory:
+    @staticmethod
+    def create_agent(
+        conversation_agent_choice: str,
+        agent_settings: dict,
+        llm_configs: dict,
+        system_prompt: str,
+        live2d_model=None,
+        tts_preprocessor_config=None,
+        **kwargs,
+    ) -> Type[AgentInterface]:
+        """Create an agent based on the configuration.
+
+        Args:
+            conversation_agent_choice: The type of agent to create
+            agent_settings: Settings for different types of agents
+            llm_configs: Pool of LLM configurations
+            system_prompt: The system prompt to use
+            live2d_model: Live2D model instance for expression extraction
+            tts_preprocessor_config: Configuration for TTS preprocessing
+            **kwargs: Additional arguments
+        """
+        logger.info(f"Initializing agent: {conversation_agent_choice}")
+
+        if conversation_agent_choice == "basic_memory_agent":
+            # Get the LLM provider choice from agent settings
+            basic_memory_settings: dict = agent_settings.get("basic_memory_agent", {})
+            llm_provider: str = basic_memory_settings.get("llm_provider")
+
+            if not llm_provider:
+                raise ValueError("LLM provider not specified for basic memory agent")
+
+            # Get the LLM config for this provider
+            llm_config: dict = llm_configs.get(llm_provider)
+            interrupt_method: Literal["system", "user"] = llm_config.pop(
+                "interrupt_method", "user"
+            )
+
+            if not llm_config:
+                raise ValueError(
+                    f"Configuration not found for LLM provider: {llm_provider}"
+                )
+
+            # Create the stateless LLM
+            llm = StatelessLLMFactory.create_llm(
+                llm_provider=llm_provider, system_prompt=system_prompt, **llm_config
+            )
+
+            tool_prompts = kwargs.get("system_config", {}).get("tool_prompts", {})
+
+            # Extract MCP components/data needed by BasicMemoryAgent from kwargs
+            tool_manager: Optional[ToolManager] = kwargs.get("tool_manager")
+            tool_executor: Optional[ToolExecutor] = kwargs.get("tool_executor")
+            mcp_prompt_string: str = kwargs.get("mcp_prompt_string", "")
+
+            # Create the agent with the LLM and live2d_model
+            return BasicMemoryAgent(
+                llm=llm,
+                system=system_prompt,
+                live2d_model=live2d_model,
+                tts_preprocessor_config=tts_preprocessor_config,
+                faster_first_response=basic_memory_settings.get(
+                    "faster_first_response", True
+                ),
+                segment_method=basic_memory_settings.get("segment_method", "pysbd"),
+                use_mcpp=basic_memory_settings.get("use_mcpp", False),
+                interrupt_method=interrupt_method,
+                tool_prompts=tool_prompts,
+                tool_manager=tool_manager,
+                tool_executor=tool_executor,
+                mcp_prompt_string=mcp_prompt_string,
+            )
+
+        elif conversation_agent_choice == "mem0_agent":
+            from .agents.mem0_llm import LLM as Mem0LLM
+
+            mem0_settings = agent_settings.get("mem0_agent", {})
+            if not mem0_settings:
+                raise ValueError("Mem0 agent settings not found")
+
+            # Validate required settings
+            required_fields = ["base_url", "model", "mem0_config"]
+            for field in required_fields:
+                if field not in mem0_settings:
+                    raise ValueError(
+                        f"Missing required field '{field}' in mem0_agent settings"
+                    )
+
+            return Mem0LLM(
+                user_id=kwargs.get("user_id", "default"),
+                system=system_prompt,
+                live2d_model=live2d_model,
+                **mem0_settings,
+            )
+
+        elif conversation_agent_choice == "hume_ai_agent":
+            settings = agent_settings.get("hume_ai_agent", {})
+            return HumeAIAgent(
+                api_key=settings.get("api_key"),
+                host=settings.get("host", "api.hume.ai"),
+                config_id=settings.get("config_id"),
+                idle_timeout=settings.get("idle_timeout", 15),
+            )
+
+        elif conversation_agent_choice == "letta_agent":
+            settings = agent_settings.get("letta_agent", {})
+            return LettaAgent(
+                live2d_model=live2d_model,
+                id=settings.get("id"),
+                tts_preprocessor_config=tts_preprocessor_config,
+                faster_first_response=settings.get("faster_first_response"),
+                segment_method=settings.get("segment_method"),
+                host=settings.get("host"),
+                port=settings.get("port"),
+            )
+
+        else:
+            raise ValueError(f"Unsupported agent type: {conversation_agent_choice}")