CO

CosyVoice

Audio / Speech·application·open·#449 of 944·+18·Rising

72.1

Moderate

High confidence
WebsiteGitHub

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

Pillar Breakdown

Adoption

35%

85.3

Maintenance

30%

59.8

Friction

20%

99.9

Ecosystem

15%

47.9

Momentum

0.74Rising
7d change +0.82
High confidence

In Audio / Speech

Ranked #20 of 36

1NeMo
87.0
2WhisperX
83.7
3edge-tts
81.0
4Coqui TTS
80.8
5sherpa-onnx
79.6
6MockingBird
79.0
7VoxCPM
78.7
8Faster Whisper
78.6
See all 36 in Audio / Speech →

Similar Tools

SM

silero-models

Audio / Speech

71.6

ZO

Zonos

Audio / Speech

71.5

MA

mlx-audio

Audio / Speech

72.7

VI

vits

Audio / Speech

72.8