GraphCanon
Home/Model Training/VibeVoice-ComfyUI
VibeVoice-ComfyUI logo

VibeVoice-ComfyUI

Enrichment pending
Enemyx-net/VibeVoice-ComfyUI

A comprehensive ComfyUI integration for Microsoft's VibeVoice text-to-speech model, enabling high-quality single and multi-speaker voice synthesis directly within your ComfyUI workflows.

GitHub

GraphCanon updated today · GitHub synced today

1.5k
Stars
243
Forks
34
Open issues
18
Watchers
4mo
Last push
Python MITCreated Aug 27, 2025

Trust & integrity

Full report
Maintenance
Slowing (143d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Personal account
As of today · Source: github_public_v1
Security (OSV)
51 low (51 low)
As of today · Source: osv@v1

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Overview

A comprehensive ComfyUI integration for Microsoft's VibeVoice text-to-speech model, enabling high-quality single and multi-speaker voice synthesis directly within your ComfyUI workflows.

Capability facts

Languages
python

Source: github.language+pyproject.toml · Jul 11, 2026

Categories

Model TrainingSpeech & AudioDeveloper Tools

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 11, 2026)

- Ensure you're using ComfyUI's Python environment
Source link

Tags

comfyui-custom-nodes-text-to-speechai-ttsai-voice-cloneai-audiocomfyui-nodesai-voice-cloniningcomfyui-custom-nodeai-voice

README

Compatibility & Installation

  • 📦 Self-Contained: Embedded VibeVoice code, no external dependencies
  • 🔄 Universal Compatibility: Adaptive support for transformers v4.51.3+
  • 🖥️ Cross-Platform: Works on Windows, Linux, and macOS
  • 🎮 Multi-Backend: Supports CUDA, CPU, and MPS (Apple Silicon)

Automatic Installation (Recommended)

  1. Clone this repository into your ComfyUI custom nodes folder:
cd ComfyUI/custom_nodes
git clone https://github.com/Enemyx-net/VibeVoice-ComfyUI
  1. Restart ComfyUI - the nodes will automatically install requirements on first use

Installation Steps

  1. Create the models folder if it doesn't exist:

    ComfyUI/models/vibevoice/

  2. Download and organize files in the vibevoice folder:

    ComfyUI/models/vibevoice/
├── tokenizer/                 # Place Qwen tokenizer files here
│   ├── tokenizer_config.json
│   ├── vocab.json
│   ├── merges.txt
│   └── tokenizer.json
├── VibeVoice-1.5B/           # Model folder
│   ├── config.json
│   ├── model-00001-of-00003.safetensors
│   ├── model-00002-of-00003.safetensors
│   └── ... (other model files)
├── VibeVoice-Large/
│   └── ... (model files)
└── my-custom-vibevoice/      # custom names are supported
    └── ... (model files)

  3. For models downloaded from HuggingFace using git-lfs or the HF CLI, you can also use the cache structure:

    ComfyUI/models/vibevoice/
└── models--microsoft--VibeVoice-1.5B/
    └── snapshots/
        └── [hash]/
            └── ... (model files)

  4. Refresh your browser - the models will appear in the dropdown menu

Hardware

  • Minimum: 8GB VRAM for VibeVoice-1.5B
  • Recommended: 17GB+ VRAM for VibeVoice-Large
  • RAM: 16GB+ system memory

Installation Issues

  • Ensure you're using ComfyUI's Python environment
  • Try manual installation if automatic fails
  • Restart ComfyUI after installation

📄 License

This ComfyUI wrapper is released under the MIT License. See LICENSE file for details.

Note: The VibeVoice model itself is subject to Microsoft's licensing terms:

  • VibeVoice is for research purposes only
  • Check Microsoft's VibeVoice repository for full model license details