CosyVoice
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
QwenAudio/CosyVoice
View on GitHub ↗Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
CosyVoice grew +1.5% in the last 30 days, ranks 7th of 76 in Audio / Speech Models, last commit 150 days ago.
Star trajectory
89 days tracked2026-07-2624.1k stars today2026-10-23
Momentum
+1.5% in 30d, above the Audio / Speech Models median of +0.2%.
Maintenance
Last commit 150 days ago, fresher than the median of 275d.
How it compares in Audio / Speech Models
CosyVoice
24.1k
stars
+1.5% 30d
commit 150 days ago
Audio / Speech Models median
1.9k
stars
+0.2% 30d
commit ~275d ago
Leader · GPT-SoVITS
63.6k
stars
+2.4% 30d
commit 3 days ago
Ranked 7th of 76 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 51
- Forks
- 2.8k
- Watchers
- 136
- Open issues
- 622
- Releases
- 0
- Created
- 2024-07-03
- Stars this week
- +98
You've seen where CosyVoice stands today.
Get the moves before everyone else: the 5 Audio / Speech Models repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.