ComfyUI GPT_SoVITS

new repo https://github.com/AIFSH/GSTTS-ComfyUI

ComfyUI-GPT_SoVITS

a comfyui custom node for GPT-SoVITS! you can voice cloning and tts in comfyui now

Disclaimer / Disclaimer

We do not hold any responsibility for any illegal usage of the codebase. Please refer to your local laws about DMCA and other related laws.

Features

• srt file for subtitle was supported
• mutiple speaker was supported in finetune and inference by srt
• huge comfyui custom nodes can merge in gpt_sovits

How to use

make sure ffmpeg is worked in your commandline for Linux

 apt update
apt install ffmpeg

for Windows, you can install ffmpeg by WinetUI automatically

Then!

 git clone https://github.com/AIFSH/ComfyUI-GPT_SoVITS.git
cd ComfyUI-GPT_SoVITS
pip install -r requirements.txt

weights will be downloaded from huggingface automatically! if you in china,make sure your internet attach the huggingface or if you still struggle with huggingface, you may try following hf-mirror to config your env.

Or download the weight file and decompress it, put the entire folder of pretrained_models into ComfyUI-GPT_SoVITS directory

Windows

There is a portable standalone build for Windows that should work for running on Nvidia GPUs and cuda>=11.8, click the link to download

Tutorial

• Demo
• Demo for mutiple speaker
• FULL WorkFLOW

My other nodes you may need

• ComfyUI-UVR5
• ComfyUI-IP_LAP

WeChat Group && Donate

Thanks

• GPT-SoVITS