CosyVoice

• 2025/12

  • 发布 Fun-CosyVoice3-0.5B-2512 基础模型、强化学习模型及其训练/推理脚本
  • 发布 Fun-CosyVoice3-0.5B ModelScope Gradio 空间

• 2025/08

  • 感谢 NVIDIA Yuekai Zhang 的贡献，添加了 Triton TRTLLM 运行时支持以及 CosyVoice2 GRPO 训练支持

• 2025/07

  • 发布 Fun-CosyVoice 3.0 评测集

• 2025/05

  • 添加 CosyVoice2-0.5B vLLM 支持

• 2024/12

  • 发布 25Hz CosyVoice2-0.5B

• 2024/09

  • 25Hz CosyVoice-300M 基础模型
  • 25Hz CosyVoice-300M 声音转换功能

• 2024/08

  • 为 LLM 稳定性添加重复感知采样（RAS）推理
  • 支持流式推理模式，包括用于 RTF 优化的 KV 缓存和 SDPA

• 2024/07

  • 支持 Flow Matching 训练
  • 在 ttsfrd 不可用时支持 WeTextProcessing
  • FastAPI 服务器和客户端

评测

安装

克隆并安装

• 克隆仓库

  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
  

• 安装 Conda：请参阅 https://docs.conda.io/en/latest/miniconda.html

• 创建 Conda 环境：

  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
  

模型下载

我们强烈建议您下载我们预训练的 Fun-CosyVoice3-0.5B CosyVoice2-0.5B CosyVoice-300M CosyVoice-300M-SFT CosyVoice-300M-Instruct 模型和 CosyVoice-ttsfrd 资源。

# modelscope SDK model download
from modelscope import snapshot_download
snapshot_download('FunAudioLLM/Fun-CosyVoice3-0.5B-2512', local_dir='pretrained_models/Fun-CosyVoice3-0.5B')
snapshot_download('iic/CosyVoice2-0.5B', local_dir='pretrained_models/CosyVoice2-0.5B')
snapshot_download('iic/CosyVoice-300M', local_dir='pretrained_models/CosyVoice-300M')
snapshot_download('iic/CosyVoice-300M-SFT', local_dir='pretrained_models/CosyVoice-300M-SFT')
snapshot_download('iic/CosyVoice-300M-Instruct', local_dir='pretrained_models/CosyVoice-300M-Instruct')
snapshot_download('iic/CosyVoice-ttsfrd', local_dir='pretrained_models/CosyVoice-ttsfrd')

# for oversea users, huggingface SDK model download
from huggingface_hub import snapshot_download
snapshot_download('FunAudioLLM/Fun-CosyVoice3-0.5B-2512', local_dir='pretrained_models/Fun-CosyVoice3-0.5B')
snapshot_download('FunAudioLLM/CosyVoice2-0.5B', local_dir='pretrained_models/CosyVoice2-0.5B')
snapshot_download('FunAudioLLM/CosyVoice-300M', local_dir='pretrained_models/CosyVoice-300M')
snapshot_download('FunAudioLLM/CosyVoice-300M-SFT', local_dir='pretrained_models/CosyVoice-300M-SFT')
snapshot_download('FunAudioLLM/CosyVoice-300M-Instruct', local_dir='pretrained_models/CosyVoice-300M-Instruct')
snapshot_download('FunAudioLLM/CosyVoice-ttsfrd', local_dir='pretrained_models/CosyVoice-ttsfrd')

可选地，您可以解压 ttsfrd 资源并安装 ttsfrd 包以获得更好的文本规范化性能。

请注意，此步骤并非必需。如果您不安装 ttsfrd 包，我们将默认使用 wetext。

cd pretrained_models/CosyVoice-ttsfrd/
unzip resource.zip -d .
pip install ttsfrd_dependency-0.1-py3-none-any.whl
pip install ttsfrd-0.4.2-cp310-cp310-linux_x86_64.whl

基本用法

我们强烈建议使用 Fun-CosyVoice3-0.5B 以获得更好的性能。 请遵循 example.py 中的代码以了解每个模型的详细用法。

python example.py

vLLM 用法

CosyVoice2/3 现在支持 vLLM 0.11.x+ (V1 引擎) 和 vLLM 0.9.0 (旧版)。 旧版 vllm 版本(<0.9.0) do not support CosyVoice inference, and versions in between (e.g., 0.10.x) are not tested.

Notice that vllm has a lot of specific requirements. You can create a new env to in case your hardward do not support vllm and old env is corrupted.

conda create -n cosyvoice_vllm --clone cosyvoice
conda activate cosyvoice_vllm
# for vllm==0.9.0
pip install vllm==v0.9.0 transformers==4.51.3 numpy==1.26.4 -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
# for vllm>=0.11.0
pip install vllm==v0.11.0 transformers==4.57.1 numpy==1.26.4 -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host=mirrors.aliyun.com
python vllm_example.py

Start web demo

You can use our web demo page to get familiar with CosyVoice quickly.

Please see the demo website for details.

# change iic/CosyVoice-300M-SFT for sft inference, or iic/CosyVoice-300M-Instruct for instruct inference
python3 webui.py --port 50000 --model_dir pretrained_models/CosyVoice-300M

Advanced Usage

For advanced users, we have provided training and inference scripts in examples/libritts.

Build for deployment

Optionally, if you want service deployment, You can run the following steps.

cd runtime/python
docker build -t cosyvoice:v1.0 .
# change iic/CosyVoice-300M to iic/CosyVoice-300M-Instruct if you want to use instruct inference
# for grpc usage
docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/grpc && python3 server.py --port 50000 --max_conc 4 --model_dir iic/CosyVoice-300M && sleep infinity"
cd grpc && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>
# for fastapi usage
docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/fastapi && python3 server.py --port 50000 --model_dir iic/CosyVoice-300M && sleep infinity"
cd fastapi && python3 client.py --port 50000 --mode <sft|zero_shot|cross_lingual|instruct>

Using Nvidia TensorRT-LLM for deployment

Using TensorRT-LLM to accelerate cosyvoice2 llm could give 4x acceleration comparing with huggingface transformers implementation. To quick start:

cd runtime/triton_trtllm
docker compose up -d

For more details, you could check here

Discussion & Communication

You can directly discuss on Github Issues.

You can also scan the QR code to join our official Dingding chat group.

Acknowledge

1. We borrowed a lot of code from FunASR.
2. We borrowed a lot of code from FunCodec.
3. We borrowed a lot of code from Matcha-TTS.
4. We borrowed a lot of code from AcademiCodec.
5. We borrowed a lot of code from WeNet.

Citations

@article{du2024cosyvoice,
  title={Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens},
  author={Du, Zhihao and Chen, Qian and Zhang, Shiliang and Hu, Kai and Lu, Heng and Yang, Yexin and Hu, Hangrui and Zheng, Siqi and Gu, Yue and Ma, Ziyang and others},
  journal={arXiv preprint arXiv:2407.05407},
  year={2024}
}

@article{du2024cosyvoice,
  title={Cosyvoice 2: Scalable streaming speech synthesis with large language models},
  author={Du, Zhihao and Wang, Yuxuan and Chen, Qian and Shi, Xian and Lv, Xiang and Zhao, Tianyu and Gao, Zhifu and Yang, Yexin and Gao, Changfeng and Wang, Hui and others},
  journal={arXiv preprint arXiv:2412.10117},
  year={2024}
}

@article{du2025cosyvoice,
  title={CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training},
  author={Du, Zhihao and Gao, Changfeng and Wang, Yuxuan and Yu, Fan and Zhao, Tianyu and Wang, Hao and Lv, Xiang and Wang, Hui and Shi, Xian and An, Keyu and others},
  journal={arXiv preprint arXiv:2505.17589},
  year={2025}
}

@inproceedings{lyu2025build,
  title={Build LLM-Based Zero-Shot Streaming TTS System with Cosyvoice},
  author={Lyu, Xiang and Wang, Yuxuan and Zhao, Tianyu and Wang, Hao and Liu, Huadai and Du, Zhihao},
  booktitle={ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={1--2},
  year={2025},
  organization={IEEE}
}

生态系统

CosyVoice 是 FunAudioLLM 家族的一部分——一个完整的语音 AI 工具包：

免责声明

以上内容仅供学术目的使用，旨在展示技术能力。部分示例来源于互联网。如果任何内容侵犯了您的权利，请联系我们请求删除。