nodes/hay86-ComfyUI_OpenVoice

Fork 0

T

hay86 cd2faa1f7d add v2 support

2024-05-14 11:56:35 +00:00

docs

Update USAGE.md

2024-04-23 13:06:31 -04:00

examples

forget examples folder

2024-04-12 10:47:11 +00:00

openvoice

Merge branch 'main' of https://github.com/myshell-ai/OpenVoice into myshell-ai-main

2024-05-14 11:55:48 +00:00

resources

update example reference

2024-04-20 12:56:29 -04:00

__init__.py

first commit

2024-04-12 10:45:09 +00:00

.gitignore

Merge branch 'main' of https://github.com/myshell-ai/OpenVoice into myshell-ai-main

2024-05-14 11:55:48 +00:00

demo_part1.ipynb

update v2

2024-04-17 21:08:27 +00:00

demo_part2.ipynb

update v2

2024-04-17 21:08:27 +00:00

demo_part3.ipynb

update v2

2024-04-17 21:08:27 +00:00

LICENSE

update v2

2024-04-17 21:08:27 +00:00

nodes.py

add v2 support

2024-05-14 11:56:35 +00:00

README.md

add v2 support

2024-05-14 11:56:35 +00:00

README.md.bak

add v2 support

2024-05-14 11:56:35 +00:00

requirements.txt

first commit

2024-04-12 10:45:09 +00:00

requirements.txt.bak

first commit

2024-04-12 10:45:09 +00:00

setup.py

fix find packages

2024-04-27 17:37:37 +02:00

README.md

ComfyUI OpenVoice (Unofficial Support)

Unofficial OpenVoice support for ComfyUI.

Important Updates

2024/05/14: Added OpenVoice V2 support (needs extra installation)
2024/04/12: Added ComfyUI nodes and workflow examples

Basic Workflow

This workflow shows the basic usages on (1) text-to-speech (TTS) and (2) speech-to-speech (STS) using reference voice. NOTE: Chinese language only supports default style.

Installation

Install from ComfyUI Manager (search for openvoice, make sure ffmpeg is installed)
Download or git clone this repository into the ComfyUI/custom_nodes/ directory and run:

sudo apt install ffmpeg
pip install -r requirements.txt

Extra Installation for V2

apt get install mecab libmecab-dev
pip install git+https://github.com/myshell-ai/MeloTTS.git
python -m unidic download

Download Checkpoints

All the models are downloaded automatically, no worries.