myshell-ai/OpenVoice

Instant voice cloning by MIT and MyShell. Audio foundation model.

49
/ 100
Emerging

This tool helps content creators, marketers, or educators quickly clone a voice from a short audio sample. It takes a few seconds of spoken audio of a person's voice and text you provide, then generates new speech in that cloned voice, even in different languages. This is ideal for anyone needing consistent voiceovers or narration without re-recording.

36,111 stars. No commits in the last 6 months.

Use this if you need to generate high-quality, natural-sounding speech in a specific voice from text, with control over emotion, accent, and other stylistic elements.

Not ideal if you primarily need to transcribe audio or perform complex audio editing tasks beyond voice generation.

content-creation voice-acting e-learning marketing-audio localization
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

36,111

Forks

4,033

Language

Python

License

MIT

Last pushed

Apr 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/myshell-ai/OpenVoice"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.