CosyVoice

Text-to-Speech

QwenAudio/CosyVoice

24.2K2.8KPythonApache-2.0

An open-source multilingual voice generation model from Alibaba that clones a voice from a few seconds of audio and produces natural-sounding speech.

🗣️ Text-to-Speech🏷️ Podcast Audio🏷️ Video Editing

CosyVoice preview — Preview card generated by GitHub from the repository. Star counts on the card may lag behind the figures above.

Tool Info

Type🐙 Open Source

Stars24.2K

Forks2.8K

LanguagePython

LicenseApache-2.0

Unlock the full analysis — free

You're reading the public preview of CosyVoice. The AI-written pros & cons, use cases, setup guide and audience fit are free with an account — no credit card. Pro adds AI comparisons (50 per 30 days) and member daily & weekly reports.

Let your AI agent install it

Copy this and paste it into Claude Code, Codex, Cursor, or any assistant that can run commands. It will install and verify on your OS.

Install and configure CosyVoice on my machine.
Repository: https://github.com/QwenAudio/CosyVoice

Requirements:
1. Read the repo's README and install docs first — confirm system requirements, dependencies, and the officially supported install path. Don't guess commands.
2. Choose steps for my OS (macOS / Linux / Windows). If unsure, ask me first — no destructive operations.
3. After installing, run a minimal working example and paste the real output, so we know it actually runs.
4. Ask before you need an API key, admin rights, or a large download / significant disk usage.
5. Finally tell me in a few lines: how to start it, how to uninstall it, and where the config lives.

Compare CosyVoice with alternatives

See how it stacks up against other text-to-speech tools.

More Tools

VoiceStudio

88.9K

A fully local, open-source voice toolkit for cloning voices, dubbing videos, transcribing audio and creating audiobooks in 646 languages.

GPT-SoVITS

63.8K

Clone a voice with just one minute of audio and generate realistic speech.

VibeVoice

55.0K

An open-source AI voice tool that generates natural and realistic speech, suitable for a variety of voice content creation.

VoxCPM

40.7K

VoxCPM2 is an open-source speech synthesis tool that can generate multilingual speech, creative voices, and clone real human voices.

bark

39.3K

An AI tool that generates realistic speech, music, and sound effects from text, making it easy for ordinary people to create audio content.