Instructions to use ResembleAI/chatterbox with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Chatterbox
How to use ResembleAI/chatterbox 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) - Inference
- Notebooks
- Google Colab
- Kaggle
Can I use original voice recordings from demo page?
Thank You for that project, it is really amazing.
Can You please tell me: can I use voices that are used in chatterbox demo page:
https://huggingface.co/spaces/ResembleAI/Chatterbox-Multilingual-TTS
There is this dropdown for language reference audio file and it lists voices for many languages. I would like to use them to generate audio for my projects. Is it ok to use them in my commercial projects?
Thank You for information
Hello Resemble AI team, thank you for Chatterbox. Could you clarify the permissions for the French reference audio fr_f1.flac supplied in your official multilingual demo (https://storage.googleapis.com/chatterbox-demo-samples/mtl_prompts/fr_f1.flac)?
We would like to use narration generated with this reference in original educational videos on YouTube and TikTok, including monetized videos. We understand the model/software is MIT-licensed; our question concerns the reference recording and the speaker permissions specifically.
Does your authorization cover this commercial use of generated speech? Are attribution, disclosure, or other conditions required? A link to the applicable permission or terms would be helpful. Thank you.