VibeVoice ComfyUI Nodes

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.

✨ Features

Core Functionality

• 🎤 Single Speaker TTS: Generate natural speech with optional voice cloning

• 👥 Multi-Speaker Conversations: Support for up to 4 distinct speakers

• 🎯 Voice Cloning: Clone voices from audio samples

• 🎨 LoRA Support: Fine-tune voices with custom LoRA adapters (v1.4.0+)

• 🎚️ Voice Speed Control: Adjust speech rate by modifying reference voice speed (v1.5.0+)

• 📝 Text File Loading: Load scripts from text files

• 📚 Automatic Text Chunking: Handles long texts seamlessly with configurable chunk size

• ⏸️ Custom Pause Tags: Insert silences with [pause] and [pause:ms] tags (wrapper feature)

• 🔄 Node Chaining: Connect multiple VibeVoice nodes for complex workflows

• ⏹️ Interruption Support: Cancel operations before or between generations

• 🔧 Flexible Configuration: Control temperature, sampling, and guidance scale

Performance & Optimization

• ⚡ Attention Mechanisms: Choose between auto, eager, sdpa, flash_attention_2 or sage

• 🎛️ Diffusion Steps: Adjustable quality vs speed trade-off (default: 20)

• 💾 Memory Management: Toggle automatic VRAM cleanup after generation

• 🧹 Free Memory Node: Manual memory control for complex workflows

• 🍎 Apple Silicon Support: Native GPU acceleration on M1/M2/M3 Macs via MPS

• 🔢 8-Bit Quantization: Perfect audio quality with high VRAM reduction

• 🔢 4-Bit Quantization: Maximum VRAM savings with minimal quality loss