Sign In
C

CosyVoice

FunAudioLLM open model family for multilingual and expressive speech synthesis.

AIopen source

Setup complexity

hard

Platforms

Windows, macOS, Linux

Current version

Not specified

Latest activity signal

GitHub commit 5/25/2026

Original release date

7/3/2024

Current version release date

Not specified

Freshness score

85/100

Overview

CosyVoice is an open-source model family for multilingual text-to-speech with practical deployment support.

Integrations

GitHubModelScope

Get the weekly tool roundup

Keep up with tools like CosyVoice. One concise email per week.