Sign in

Nodes Browser

ComfyDeploy: How ComfyUI-Zonos works in ComfyUI?

What is ComfyUI-Zonos?

TTS with Zyphra Zonos

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-Zonos and select it
  5. Close the build step dialig and then click on the "Save" button to rebuild the machine

ComfyUI-Zonos

ComfyUI node to make text to speech audio with your own voices.

ComfyUI-Zonos

** Currently only tested on Windows **

Installation

  • You can git clone https://github.com/BuffMcBigHuge/ComfyUI-Zonos into custom_nodes or install from ComfyUI-Manager
cd custom_nodes/ComfyUI-Zonos
git submodule update --init --recursive
pip install -r requirements.txt
git clone https://github.com/Zyphra/Zonos.git

You will need to install eSpeak NG on your machine.

  • Windows: You can install eSpeak NG then have to set PHONEMIZER_ESPEAK_LIBRARY=C:\Program Files\eSpeak NG\libespeak-ng.dll in your environment variables, and restart your terminal.
  • Linux: You can install via sudo apt install -y espeak-ng.
  • You may need to install CUDA Toolkit to use the GPU as well as Visual Studio Build Tools to compile.

How To Use

  • Drop a .wav file into ComfyUI/input of a short (5-10s) clear audio of the voice you'd like to use.
  • And a .txt file of the same name with what was said.
  • Tap "R" in ComfyUI to refresh the node list.
  • Use the ZonosGenerate and queue a prompt, (Example Workflow).

Current Issues

  • Untested on Mac/Linux
  • Model loading isn't handled by Comfy native - ymmv
  • Can't get compiling to work - will update when fixed

Special Thanks

  • Zyphra for the Zonos model.
  • niknah for the F5-TTS node.
  • sdbds for the Zonos-for-windows gradio_interface.py