OpenVoice
Stalled — excluded
★ pending verification stars, verified 2026-09-30Category: Voice: TTS / STT / CloningGitHub repository ↗
No direct GitHub link yet — star count pending verification before we write it up.
Stalled — excluded.
Text-to-speech, speech-to-text, and voice cloning, open source.
Key features
- Clones reference tone color to generate speech in multiple languages and accents
- Granular control over emotion, accent, rhythm, pauses and intonation
- Zero-shot cross-lingual voice cloning without the language in training data
- OpenVoice V2 adds native support for 6 languages and better audio quality
Good for
- Instant voice cloning for apps and chatbots, as used by myshell.ai
- Multilingual speech generation from a short voice sample
- Developers needing free-for-commercial-use MIT voice cloning
Stack & tags
voice-cloningttsopen-weightsmultilingualzero-shotmit-license
Similar open-source projects
Whisper
★ 109,795OpenAI's open-source speech recognition model — the benchmark for multilingual STT
GPT-SoVITS
★ 62,271TTS/cloning trainable on 1 minute of audio — a legendary Chinese-community project