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

<div> <figure> <img alt='webpage' src="web.png?raw=true" width="600px"/> <figure> </div>

Disclaimer / 免责声明

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. 我们不对代码库的任何非法使用承担任何责任. 请参阅您当地关于 DMCA (数字千年法案) 和其他相关法律法规.

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 WingetUI 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 follow hf-mirror to config your env.

或者下载权重文件解压后把pretrained_models整个文件夹放进ComfyUI-GPT_SoVITS目录

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

<div> <figure> <img alt='Wechat' src="1key.jpg?raw=true" width="300px"/> <figure> </div>

Tutorial

• Demo
• Demo for mutiple speaker
• FULL WorkFLOW

My other nodes you may need

• ComfyUI-UVR5
• ComfyUI-IP_LAP

WeChat Group && Donate

<div> <figure> <img alt='Wechat' src="wechat.jpg?raw=true" width="300px"/> <img alt='donate' src="donate.jpg?raw=true" width="300px"/> <figure> </div>

Thanks

• GPT-SoVITS