MW-ComfyUI_OuteTTS

OuteTTS - Unified Text-To-Speech. A node for ComfyUI

By billwuhao·Created about a year ago·Updated about a year ago· 10

billwuhao/ComfyUI_OuteTTS

Nodes—

On cloudLocal install

Stars10

Updatedabout a year ago

Readme

中文|English

QuteTTS ComfyUI Node

Text-to-speech, voice cloning (source audio up to 20 seconds), auto-saving speakers.

Clean, loud, and clear voice cloning works best.

📣 Updates

[2025-04-14] ⚒️: Released v1.0.0.

Installation

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

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

Model Downloads

Llama-OuteTTS-1.0-1B: Download and place in the ComfyUI/models/TTS directory.
weights_24khz_1.5kbps_v1.0.pth: Download and place in the ComfyUI/models/TTS/DAC.speech.v1.0 directory.
whisper-large-v3-turbo: Download and place in the ComfyUI/models/TTS/whisper-large-v3-turbo directory.

Acknowledgements

OuteTTS