OpenVoice
View on GitHubInstant voice cloning by MIT and MyShell. Audio foundation model.
OpenVoice is a Python toolkit for instant voice cloning and text-to-speech. It supports zero-shot cross-lingual cloning and controls for emotion, accent, rhythm, pauses, and intonation; V2 natively supports English, Spanish, French, Chinese, Japanese, and Korean.
Use Cases
Clone a voice from a reference audio sampleGenerate speech in multiple languages and accentsControl emotion, rhythm, pauses, and intonationBuild voice-cloning demos and applications
Built With
- Language
- Python
- Frameworks
- TTS · VITS · VITS2 · Gradio
Tags
text-to-speech · voice cloning · zero-shot TTS · cross-lingual · voice style control · speech generation