FunAudioLLM/CosyVoice

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

64
/ 100
Established

This project helps create high-quality, natural-sounding voiceovers from written text across many languages and dialects. You provide text, and it generates realistic spoken audio, even allowing for customization of emotion, speed, and volume. This is ideal for content creators, educators, or businesses needing automated voice production for various applications.

19,991 stars. Actively maintained with 6 commits in the last 30 days.

Use this if you need to transform written content into spoken audio with high naturalness and speaker consistency across multiple languages and Chinese dialects, including zero-shot voice cloning.

Not ideal if you require only basic text-to-speech for a single language without advanced customization or high-fidelity output.

voice-generation content-creation e-learning localization audio-production
No Package No Dependents
Maintenance 17 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

19,991

Forks

2,270

Language

Python

License

Apache-2.0

Last pushed

Feb 11, 2026

Commits (30d)

6

Get this data via API

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

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