Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
ComfyUI custom node for the VibeVoice TTS. Expressive, long-form, multi-speaker conversational audio
| Date | Stars |
|---|---|
| 2026-07-30 | 589 |
| 2026-08-07 | 593 |
| 2026-08-15 | 595 |
| 2026-08-18 | 595 |
| 2026-08-20 | 596 |
| 2026-08-28 | 597 |
| 2026-09-08 | 596 |
| 2026-09-13 | 597 |
| 2026-09-24 | 596 |
| 2026-09-27 | 595 |
| 2026-09-30 | 597 |
| 2026-10-01 | 598 |
| 2026-10-04 | 599 |
| 2026-10-05 | 599 |
| 2026-10-06 | 600 |
| 2026-10-09 | 601 |
| 2026-10-10 | 603 |
| 2026-10-11 | 604 |
| 2026-10-12 | 604 |
| 2026-10-15 | 605 |
| 2026-10-16 | 606 |
| 2026-10-19 | 607 |
| 2026-10-21 | 607 |
| 2026-10-22 | 606 |
| 2026-10-25 | 607 |
| 2026-10-26 | 607 |
| 2026-10-27 | 607 |
| 2026-10-28 | 608 |
| 2026-10-29 | 609 |
| 2026-10-30 | 610 |
| 2026-10-31 | 611 |
| 2026-11-03 | 612 |
| 2026-11-04 | 611 |
Today
-1 stars today
This week
+3 stars this week
This month
+12 stars this month
Momentum
38.0
growth rate 0.49%/day
<a id="readme-top"></a>
<div align="center">
# ComfyUI-VibeVoice
<img alt="ComfyUI-VibeVoice logo" src="https://github.com/user-attachments/assets/0b9663a1-01ab-4ad8-812b-2b60169e236c" />
Long-form, multi-speaker conversational **TTS** and **ASR** for ComfyUI.<br>
Microsoft's VibeVoice, with model download, VRAM management and audio handling handled for you.
<a href="https://github.com/wildminder/ComfyUI-VibeVoice/issues/new?labels=bug&template=bug-report---.md">Report Bug</a>
·
<a href="https://github.com/wildminder/ComfyUI-VibeVoice/issues/new?labels=enhancement&template=feature-request---.md">Request Feature</a>
[![License: MIT][license-shield]][license-url]
[![Last commit][commit-shield]][commit-url]
[![ComfyUI][comfy-shield]][comfy-url]
[![Model weights on Hugging Face][hf-shield]][hf-url]
</div>
> [!NOTE]
> **ComfyUI-VibeVoice** wraps the Microsoft [VibeVoice](https://github.com/microsoft/VibeVoice) family — 1.5B / 7B long-form conversational TTS, a 0.5B realtime model, and ASR — as native ComfyUI nodes. Models download on first run into `ComfyUI/models/tts/VibeVoice/` and load under ComfyUI's VRAM manager. Nodes appear under `WMNodes/sound/tts` and `WMNodes/sound/asr`.
<details>
<summary><b>Table of Contents</b></summary>
* [Features](#features)
* [Models](#models)
* [Getting started](#getting-started)
* [Usage](#usage)
* [Script format](#script-format)
* [Voice modes](#voice-modes)
* [Realtime models](#realtime)
* [Node inputs](#node-inputs)
* [Loading external models](#external-models)
* [Host RAM during an external load](#host-ram)
* [Performance & stability](#performance)
* [Feature compatibility & VRAM matrix](#vram-matrix)
* [`transformers` version support](#transformers-support)
* [Attention backends](#attention-backends)
* [Changelog](#changelog)
* [License](#license)
* [Acknowledgments](#acknowledgments)
* [Star history](#star-history)
</details>
<p id="features" align="center">◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆</p>
## ❖ Features
<div align="center">
<img alt="nodes" src="https://github.com/user-attachments/assets/a7e80bbf-7006-422a-aa81-45ae5001a3b2" />
<br/><br/>
</div>
| Capability | Detail |
| :--- | :--- |
| **Multi-speaker TTS** | ![TTS][task-tts] - Up to 4 distinct voices in one output |
| **Voice cloning** | ![TTS][task-tts] - Any `.wav` / `.mp3` as a speaker reference |
| **Hybrid scripts** | ![TTS][task-tts] - Cloned voices plus speakers that reuse a provided reference, in the same script |
| **Speech recognition** | ![ASR][task-asr] - `VibeVoice ASR` returns timestamped speaker segments |
| **Quantization** | ![GGUF][badge-gguf] ![fp8][badge-fp8] ![int8][badge-int8] ![int4][badge-int4] - GGUF, fp8, int8 and 4-bit, plus safetensors |
| **Attention backends** | `eager` / `sdpa` / `flash_attention_2` / `sage` |
| **Memory** | Models download and load under ComfyUI's VRAM manager |
<p id="models" align="center">◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆</p>
## ⌬ Models
Downloaded on first run into `ComfyUI/models/tts/VibeVoice/`.
| Model | Type | Size | Weights |
| :--- | :---: | :---: | :---: |
| **VibeVoice-1.5B** | ![TTS][task-tts] | 3.0 GB | [![][hf-microsoft]](https://huggingface.co/microsoft/VibeVoice-1.5B) |
| **VibeVoice-7B** | ![TTS][task-tts] | 17.4 GB | [![][hf-vibevoice]](https://huggingface.co/vibevoice/VibeVoice-7B) |
| **VibeVoice-Realtime-0.5B** | ![realtime][task-realtime] | 1.5 GB | [![][hf-microsoft]](https://huggingface.co/microsoft/VibeVoice-Realtime-0.5B) |
| **VibeVoice-ASR-HF** | ![ASR][task-asr] | 17.4 GB | [![][hf-microsoft]](https://huggingface.co/microsoft/VibeVoice-ASR-HF) |
> [!TIP]
> Quantized weights are optional. Point `Load VibeVoice Model` at a `.gguf` or a
> quantized safetensors file; leave the node unconnected to use the standard model.
<p align="right"><a href="#readme-top">⟔ ▲ ⟓ back to top</a></p>
<p id="getting-started" align="center">◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆◇◆</p>
## ⇩ Getting started
**ComfyUI Manager** — `ManaExcerpt of 30,682 characters
Read on GitHub
56
drbaph · United Kingdom
3
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:1fbf5720cc9f37d4, topic:text-to-speech, topic:tts, topic:voice-cloning