ComfyUI Extension: ComfyUI-ChatterboxTTS
ComfyUI-ChatterboxTTS is now available in ComfyUI, Chatterbox TTS is the first production-grade open-source TTS model.
Custom Nodes (0)
README
ComfyUI-ChatterboxTTS
ComfyUI-ChatterboxTTS is now available in ComfyUI, Chatterbox TTS is the first production-grade open-source TTS model.
Installation
-
Make sure you have ComfyUI installed
-
Clone this repository into your ComfyUI's custom_nodes directory:
cd ComfyUI/custom_nodes
git clone https://github.com/Yuan-ManX/ComfyUI-ChatterboxTTS.git
- Install dependencies:
cd ComfyUI-ChatterboxTTS
pip install chatterbox-tts
pip install -r requirements.txt
Model
Download Pretrained Models
Chatterbox TTS Pretrained Models
Tips
-
General Use (TTS and Voice Agents):
- The default settings (
exaggeration=0.5
,cfg_weight=0.5
) work well for most prompts. - If the reference speaker has a fast speaking style, lowering
cfg_weight
to around0.3
can improve pacing.
- The default settings (
-
Expressive or Dramatic Speech:
- Try lower
cfg_weight
values (e.g.~0.3
) and increaseexaggeration
to around0.7
or higher. - Higher
exaggeration
tends to speed up speech; reducingcfg_weight
helps compensate with slower, more deliberate pacing.
- Try lower