ComfyUI-Dia
Make Dia avialbe in ComfyUI.
Nodes (5)
The node that makes AI voices sound like actual people
The boring node that makes Dia's text box tolerable
The little node that hands Dia a voice to imitate
The node that drags a 1.6B TTS model into ComfyUI
Getting Dia's speech out of ComfyUI as an actual WAV
ComfyUI-Dia
Make Dia avialbe in ComfyUI.
A TTS model capable of generating ultra-realistic dialogue in one pass.
Dia is a 1.6B parameter text to speech model created by Nari Labs. Dia directly generates highly realistic dialogue from a transcript. You can condition the output on audio, enabling emotion and tone control. The model can also produce nonverbal communications like laughter, coughing, clearing throat, etc.
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-Dia.git
- Install dependencies:
cd ComfyUI-Dia
pip install -r requirements.txt
Model
Pretrained model checkpoints - The model weights are hosted on Hugging Face. The model only supports English generation at the moment.