ConfyUI for CosyVoice

Support both CosyVoice1.0 and CosyVoice2.0.

Referenced CosyVoice-ComfyUI, the following modifications have been made:

• Add support for CosyVoice2.0
• Add whether to use stream processing options
• Use speed control by CosyVoice
• Add model path check to avoid duplicate downloads
• Provide two ways of use

👉🏻 CosyVoice 👈🏻

CosyVoice 2.0: Demos; Paper; Modelscope; HuggingFace

CosyVoice 1.0: Demos; Paper; Modelscope

How to use

Open with ComfyUI-Manager

1. clone the repo

git clone https://github.com/SshunWang/ComfyUI_CosyVoice.git
cd ComfyUI_CosyVoice
pip install -r requirements.txt

2. load the custom node with comfyui-manager, see ComfyUI-Manager.

Auto load by ComfyUI

Copy to "your comfyui path"/custom_nodes or create a solft link to the path of this repo with ln -s command or clone to "your comfyui path"/custom_nodes directly

Example

Note

The corresponding model will be downloaded during the first use