Home/Inference & Serving/CosyVoice

CosyVoice

FunAudioLLM/CosyVoice

Multi-lingual large voice generation model with full-stack abilities for inference, training and deployment.

GitHub Website

GraphCanon updated 2d · GitHub synced 2d

23k stars2.6k forksLast push 3mo Python Apache-2.0

Decision brief

CosyVoice is a Python-based multi-lingual large voice generation model. It supports extensive capabilities including fine-tuning, TTS (Text-To-Speech), and natural language generation.

Good fit when

When you need support for multiple languages like Cantonese, Chinese, English, Japanese, and Korean.
For projects requiring comprehensive text-to-speech functionalities with a focus on cross-lingual compatibility.

Avoid when

If your project specifically requires fine-tuned performance in languages not supported by CosyVoice such as Arabic or Spanish.
When strict real-time speech synthesis requirements are essential, as CosyVoice may face delays depending on the environment's computational power and model complexity.

Observed Jul 11, 2026 · Source: enrich:decision_facts

CosyVoice alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Steady (89d since push); As of 2d
Provenance: Not a fork · Organization account; As of 2d
Security (OSV): No lockfile; As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install CosyVoice

PyPI

How it fits your stack(1)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

whisper

CosyVoice and Whisper are both models for voice generation but focus on different aspects: CosyVoice is more broadly multilingual and flexible.

Similar tools

Same-category neighbours not already linked as typed edges.

ChatTTS

A generative speech model for daily dialogue

40k★

OpenVoice

Instant voice cloning using an audio foundation model

37k★

VoxCPM

Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

34k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

CosyVoice is a multi-lingual voice generation tool that supports various languages including Cantonese, Chinese, English, Japanese, and Korean. It offers capabilities for fine-tuning, text-to-speech (TTS), voice cloning, and natural language generation. The framework is built in Python and provides tools for training, inference, and deployment.

Capability facts

Languages: python
Source: github.language · Aug 23, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Aug 23, 2026)

conda create -n cosyvoice -y python=3.10

Source link

README

Clone and install

Clone the repo

git clone --recursive https://github.com/FunAudioLLM/CosyVoice.git
# If you failed to clone the submodule due to network failures, please run the following command until success
cd CosyVoice
git submodule update --init --recursive

Install Conda: please see https://docs.conda.io/en/latest/miniconda.html

Create Conda env:

conda create -n cosyvoice -y python=3.10
conda activate cosyvoice
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com

# If you encounter sox compatibility issues
# ubuntu
sudo apt-get install sox libsox-dev
# centos
sudo yum install sox sox-devel

For agents

This page has a .md twin and JSON over the API.

/tools/funaudiollm-cosyvoice.md GET /api/graphcanon/tools/funaudiollm-cosyvoice GET /api/graphcanon/graph?tool=funaudiollm-cosyvoice