Instructions to use KitsuMate/chatterbox-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Chatterbox
How to use KitsuMate/chatterbox-onnx with Chatterbox:
# pip install chatterbox-tts import torchaudio as ta from chatterbox.tts import ChatterboxTTS model = ChatterboxTTS.from_pretrained(device="cuda") text = "Ezreal and Jinx teamed up with Ahri, Yasuo, and Teemo to take down the enemy's Nexus in an epic late-game pentakill." wav = model.generate(text) ta.save("test-1.wav", wav, model.sr) # If you want to synthesize with a different voice, specify the audio prompt AUDIO_PROMPT_PATH="YOUR_FILE.wav" wav = model.generate(text, audio_prompt_path=AUDIO_PROMPT_PATH) ta.save("test-2.wav", wav, model.sr) - Notebooks
- Google Colab
- Kaggle
| license: mit | |
| language: [en] | |
| tags: [onnx, chatterbox, text-to-speech] | |
| library_name: onnxruntime | |
| # Chatterbox ONNX | |
| KitsuMate layout of the English [ResembleAI Chatterbox](https://huggingface.co/ResembleAI/chatterbox) model using the pinned [ONNX Community export](https://huggingface.co/onnx-community/chatterbox-ONNX) at `3cab09af388d3f02bba43443fce88c1f4525ac43`. | |
| The `q4f16` variant includes the four required graphs and their external data, the English tokenizer, and the upstream default voice. The voice file is redistributed unchanged from the MIT-licensed ONNX Community repository. This is the English checkpoint; it intentionally does not include the unrelated Cangjie mapping. | |