Update banner link, add Discord/Spaces badges and Resemble logo
Browse files
README.md
CHANGED
|
@@ -18,14 +18,21 @@ base_model_relation: finetune
|
|
| 18 |
---
|
| 19 |
|
| 20 |
<p align="center">
|
| 21 |
-
<
|
|
|
|
|
|
|
| 22 |
</p>
|
| 23 |
|
| 24 |
# Dramabox — Expressive TTS with Voice Cloning
|
| 25 |
|
|
|
|
|
|
|
|
|
|
| 26 |
> **Built on [LTX-2](https://github.com/Lightricks/LTX-2) by Lightricks.**
|
| 27 |
> Dramabox is **Resemble AI's** expressive TTS, trained on top of the LTX-2.3 audio branch under the LTX-2 Community License. Huge thanks to the Lightricks team for open-sourcing the base.
|
| 28 |
|
|
|
|
|
|
|
| 29 |
Dramabox is a prompt-driven TTS where **the prompt itself controls everything** — speaker identity, emotion, delivery, laughs, sighs, breaths, pauses, transitions. An optional 10-second voice reference clones the target timbre. It is an IC-LoRA fine-tune of the **LTX-2.3 3.3B audio-only** model (Diffusion Transformer + flow matching), conditioned on Gemma 3 12B text embeddings.
|
| 30 |
|
| 31 |
| | |
|
|
|
|
| 18 |
---
|
| 19 |
|
| 20 |
<p align="center">
|
| 21 |
+
<a href="https://www.resemble.ai/learn/models/dramabox">
|
| 22 |
+
<img src="https://huggingface.co/ResembleAI/Dramabox/resolve/main/assets/Dramabox.png" alt="DramaBox" width="720"/>
|
| 23 |
+
</a>
|
| 24 |
</p>
|
| 25 |
|
| 26 |
# Dramabox — Expressive TTS with Voice Cloning
|
| 27 |
|
| 28 |
+
[](https://huggingface.co/spaces/ResembleAI/Dramabox)
|
| 29 |
+
[](https://discord.gg/rJq9cRJBJ6)
|
| 30 |
+
|
| 31 |
> **Built on [LTX-2](https://github.com/Lightricks/LTX-2) by Lightricks.**
|
| 32 |
> Dramabox is **Resemble AI's** expressive TTS, trained on top of the LTX-2.3 audio branch under the LTX-2 Community License. Huge thanks to the Lightricks team for open-sourcing the base.
|
| 33 |
|
| 34 |
+
*Made with ♥️ by* <a href="https://www.resemble.ai/learn/models/dramabox" target="_blank"><img width="100" alt="resemble-logo-horizontal" src="https://github.com/user-attachments/assets/35cf756b-3506-4943-9c72-c05ddfa4e525" /></a>
|
| 35 |
+
|
| 36 |
Dramabox is a prompt-driven TTS where **the prompt itself controls everything** — speaker identity, emotion, delivery, laughs, sighs, breaths, pauses, transitions. An optional 10-second voice reference clones the target timbre. It is an IC-LoRA fine-tune of the **LTX-2.3 3.3B audio-only** model (Diffusion Transformer + flow matching), conditioned on Gemma 3 12B text embeddings.
|
| 37 |
|
| 38 |
| | |
|