Other Voice Cloning in ComfyUI Workflow

[Nautilus]

Voice Cloning in Comfyui Workflow
For educational purposes only.

You can easily clone any voice using this workflow. This workflow can work in under 6GB VRAM so it'll work on almost all consumer GPUs


Requirements:

Custom Node: https://github.com/BuffMcBigHuge/ComfyUI-Zonos

You will need to install eSpeak NG on your machine.

• Windows: You can install eSpeak NG then have to set
  
  
  Code:

  PHONEMIZER_ESPEAK_LIBRARY=C:\Program Files\eSpeak NG\libespeak-ng.dll
  in your environment variables, and restart your terminal.
  

• Linux: You can install via
  
  
  Code:

  sudo apt install -y espeak-ng
  
  
• You may need to install CUDA Toolkit to use the GPU if you don't have it already installed
  

Model: https://huggingface.co/Zyphra/Zonos-v0.1-transformer

Download workflow: Click here