CosyVoice is an open-source speech and audio tool written in Python, released under the Apache-2.0 license. It has 24k GitHub stars and 2.7k forks, and was last updated in May 2026. Docs and downloads are linked from funaudiollm.github.io.
“Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.”
— QwenAudio, project description on GitHub
Details
| Category | Speech & Audio |
|---|---|
| GitHub stars | 24,027 |
| Forks | 2,749 |
| Language | Python |
| License | Apache-2.0 |
| Last updated | |
| Owner | QwenAudio |
| Website | funaudiollm.github.io/cosyvoice3 |
| Repository | QwenAudio/CosyVoice |
| Also listed in | Chat UIs |
Tags
audio-generationcantonesechatbotchatgptchinesecosyvoicecross-lingualenglish
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.