deploy: switch to chatterbox requirements @ f0510f6

README.md

@@ -45,43 +45,56 @@ Video → Extract Audio → Whisper Transcription → LLM Translation
 
 ---
 
-## Quick Start
+## Running Locally
 
 ### Prerequisites
 
-- Python 3.10+
-- FFmpeg installed (`brew install ffmpeg` on macOS, `sudo apt install ffmpeg` on Ubuntu)
-- OpenAI API key
+- Python 3.10+ (`requires-python = ">=3.10,<3.13"`)
+- FFmpeg (`brew install ffmpeg` on macOS, `sudo apt install ffmpeg` on Ubuntu)
+- An OpenAI API key
 
-### Setup
+### First-time setup
 
 ```bash
-# Install uv (fast Python package manager) — skip if already installed
+# 1. Install uv (skip if you already have it)
 curl -LsSf https://astral.sh/uv/install.sh | sh
 
-# Clone and install
-git clone https://github.com/yourusername/VideoVoice.git
-cd VideoVoice
-uv sync
+# 2. Clone and enter the repo
+git clone https://github.com/Video-Voice/VideoVoice-be.git
+cd VideoVoice-be
+
+# 3. Install deps with the chatterbox TTS engine (default for local dev)
+#    Use `--extra omnivoice` instead if you want OmniVoice. The two extras
+#    are mutually exclusive — pick one.
+uv sync --extra chatterbox
 
-# Configure environment
+# 4. Configure env vars
 cp .env.example .env
-# Edit .env with your API keys
+# Edit .env — at minimum set OPENAI_API_KEY and ARTIFACTS_ROOT=./data
 ```
 
-### Run the Server
+### One-time: hide the vendored chatterbox folder
+
+The repo ships a vendored `./chatterbox/` folder that the HF Chatterbox Space needs (it has ZeroGPU-specific tweaks). Locally we want Python to import the PyPI `chatterbox-tts` package instead, so tell git to ignore the working-tree state for that folder and delete it locally:
 
 ```bash
-uv run python server.py
+git ls-files chatterbox/ | xargs git update-index --skip-worktree
+rm -rf chatterbox/
 ```
 
-The app will be available at [http://localhost:8000](http://localhost:8000).
+HEAD still contains the folder, so HF deploys are unaffected. Reverse with `git update-index --no-skip-worktree` + `git checkout HEAD -- chatterbox/`.
+
+### Run the server
+
+```bash
+uv run python server.py
+```
 
-Per-job artifacts (uploads, intermediate audio, outputs) land in `ARTIFACTS_ROOT`. Set `ARTIFACTS_ROOT=./data` in your `.env` to match the layout the repo used historically — each job gets its own `data/<job_id>/` folder with every pipeline file.
+Open [http://localhost:8000](http://localhost:8000). `/api/*` are the backend routes; `/` serves the legacy static UI in `frontend/`. If the port is in use, set `PORT=8001`.
 
-### CLI Usage
+Per-job artifacts land in `$ARTIFACTS_ROOT/<job_id>/`. With `ARTIFACTS_ROOT=./data` (in `.env`) that's `./data/<job_id>/` next to the repo — same layout the repo has always used.
 
-You can also run the pipeline directly:
+### Run the pipeline headlessly
 
 ```bash
 uv run python pipeline.py --input data/my_video.mp4 --target-lang Spanish