Enemyx-net/VibeVoice-ComfyUI

Health v2 · maintenance only

Adoption not part of the score

1549 stars · 249 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A ComfyUI custom node integration for Microsoft's VibeVoice text-to-speech model, providing single and multi-speaker voice synthesis with voice cloning inside ComfyUI workflows. It supports LoRA voice fine-tuning, quantization for lower VRAM, and CUDA, CPU, and Apple Silicon MPS backends.

Use cases

• generate speech from text in comfyui workflows
• clone a voice from an audio sample
• create multi-speaker dialogue audio with up to 4 speakers
• narrate videos or audiobooks with tts nodes
• run tts locally on apple silicon or low-vram gpus
• fine-tune voices with custom lora adapters
• insert pauses and control speech speed in generated audio

When to choose

• you already use ComfyUI and want TTS or voice cloning as nodes in your workflows
• you need multi-speaker conversation synthesis or LoRA-based voice customization
• you want local, self-hosted TTS with CUDA or Apple Silicon acceleration

When to avoid

• you need a standalone TTS service or CLI outside ComfyUI
• you want fully automatic model downloads without manual setup
• you need real-time streaming TTS for live applications

Facets

plugin · maturity active

tts audio-processing machine-learning llm-inference artificial-intelligence speech-processing media windows python cross-platform comfyui comfyui-custom-node voice-cloning multi-speaker-tts vibevoice text-to-speech ai-audio lora-support quantization audio linux macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Enemyx-net/VibeVoice-ComfyUI")