Sign in

Nodes Browser

ComfyDeploy: How ComfyUI OpenVoice works in ComfyUI?

What is ComfyUI OpenVoice?

Unofficial implementation of [a/OpenVoice](https://github.com/myshell-ai/OpenVoice) for ComfyUI

How to install it in ComfyDeploy?

Head over to the machine page

  1. Click on the "Create a new machine" button
  2. Select the Edit build steps
  3. Add a new step -> Custom Node
  4. Search for ComfyUI OpenVoice and select it
  5. Close the build step dialig and then click on the "Save" button to rebuild the machine

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.