Extensions/ComfyUI_CSM
ComfyUI Extension

ComfyUI_CSM

ComfyUI node of Conversational Speech Model (CSM).

By billwuhao·Created about a year ago·Updated about a year ago· 7
billwuhao/ComfyUI_CSM
Nodes3
On cloudLocal install
Category🎤MW/MW-CSM
Stars7
Updatedabout a year ago

Nodes (3)

CSM Dialog Run
🎤MW/MW-CSM
Speakers Preview
🎤MW/MW-CSM
Multi Line Text
🎤MW/MW-CSM
Readme

中文|English

ComfyUI Node for CSM

CSM（Conversational Speech Model）, Clone voice, multi person conversation. Temporarily supports two person conversations.

📣 Update

[2025-05-29]⚒️: Re implement the core dialogue function.

[2025-03-18]⚒️: v1.0.0.

Preview

  • The prompt and text format must be as follows:
[S1] Hi, how are you.
[S2] Fine, thank you, and you?
[S1] I'm fine, too.
[S2] What are you planning to do?

  • Clone voice conversation and save speaker:

  • Load saved speakers:

Installation

cd ComfyUI/custom_nodes
git clone https://github.com/billwuhao/ComfyUI_CSM.git
cd ComfyUI_CSM
pip install -r requirements.txt

# python_embeded
./python_embeded/python.exe -m pip install -r requirements.txt

Model Download

  • csm-1b: Download config.json and model.safetensors and place them in the ComfyUI/models/TTS/csm-1b directory.

  • moshiko-pytorch-bf16: Download tokenizer-e351c8d8-checkpoint125.safetensors and place it in the ComfyUI/models/TTS/moshiko-pytorch-bf16 directory.

  • Llama-3.2-1B: Download everything except the original directory and place it in the ComfyUI\models\LLM\Llama-3.2-1B directory.

Acknowledgements

csm

Thanks to the SesameAILabs team for their excellent work 👍.