OpenVoice
An open-source voice cloning tool that generates multilingual speech from short audio clips, with emotion and accent control under the MIT license.
OpenVoice generates speech in a reference speaker's voice from a short audio clip. It's for developers and creators who need the same voice across languages or want to vary its delivery without changing the speaker.
- Voice cloning: Generate speech that reproduces the reference speaker's vocal tone using a short recording.
- Delivery control: Adjust emotion, accent, rhythm, pauses and intonation while retaining the speaker's voice, with demonstrated British, Indian and Australian accents.
- Cross-language speech: Use a reference recording in a different language from the generated speech, including languages absent from the multilingual speaker training data.
- Native language support: OpenVoice V2 natively supports English, Spanish, French, Chinese, Japanese and Korean.
The Python project is open source under the MIT license and free for commercial use. MyShell also provides hosted instant voice cloning powered by OpenVoice on its platform.
Logotyper
