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.

A ComfyUI custom node integration for local multi-engine multi-language Text-to-Speech and Voice Conversion. Supports: RVC, Echo-TTS, Qwen3-TTS, Cozy Voice 3, Step Audio EditX, IndexTTS-2, Chatterbox (classic and multilingual), F5-TTS, Higgs Audio 2 and VibeVoice with unlimited text length, SRT timing, Character support, and many audio tools

ComfyUI custom node for the VibeVoice TTS. Expressive, long-form, multi-speaker conversational audio

VibeVoiceFusion is a full-stack, multi-speaker voice generation web system featuring LoRA fine-tuning, batch generation, and VRAM optimization. Based on Microsoft's VibeVoice (AR + diffusion architecture)

A fully local and private Speech-To-Text app with cross-platform support, speaker diarization, Audio Notebook mode, LM Studio integration, and both longform and live transcription.

Audiobook creation tool supporting too many TTS models (Qwen3-TTS, OmniVoice, VibeVoice, etc), focused on high-quality output. Plus audio-synced reader app and standalone server component.

Beautiful voice app: record or upload to train a voice, generate speech from text or files, save & download voices.

Rust implementation of VibeVoice text-to-speech with voice cloning and multi-speaker synthesis.

Archive of the official Microsoft VibeVoice repository (7B & 1.5B). Backup of the deleted source code for the open-source TTS models, including the removed 7B version. Try the VibeVoice online service

Real-time voice assistant on DGX Spark with 766ms latency to first audio

ONNX speech pipeline library for ASR, diarization, VAD, and denoising

Create multi-voice podcasts with AI text-to-speech

A Gradio-based demo for end-to-end vision-to-speech inference: Extract text or descriptions from images using Qwen2.5-VL-7B-Instruct, then convert to natural speech audio via Microsoft VibeVoice-Realtime-0.5B.

HOW TO RUN MICROSOFT VIBEVOICE LOCALLY

A ready-to-use Google Colab notebook for running the open-source VibeVoice TTS model from Microsoft, using the quantized Large Q8 variant (~12 GB VRAM) for multi-speaker long-form audio generation

🐟 Enhance communication with Fish Speech, a powerful multilingual Text-to-Speech system featuring speaker management, auto-transcription, and emotion control.

Simplified scripts for fine-tuning VibeVoice speech synthesis models with LoRA. Painless fine-tuning with reasonable defaults, supporting both local GPU and Google Colab workflows.

A suckless, high-performance CLI tool for audio transcription using Microsoft VibeVoice-ASR.

🎙️ Enhance voice synthesis with ComfyUI-Qwen3-TTS, featuring advanced voice cloning, emotion-aware ASR, and unlimited multi-role dubbing.