VibeVoice

<div align="center">

## 🎙️ VibeVoice: Open-Source Frontier Voice AI
[![Project Page](https://img.shields.io/badge/Project-Page-blue?logo=githubpages)](https://microsoft.github.io/VibeVoice)
[![Hugging Face](https://img.shields.io/badge/HuggingFace-Collection-orange?logo=huggingface)](https://huggingface.co/collections/microsoft/vibevoice-68a2ef24a875c44be47b034f)
[![TTS Report](https://img.shields.io/badge/TTS-Report-red?logo=arxiv)](https://openreview.net/pdf?id=FihSkzyxdv)
[![ASR Report](https://img.shields.io/badge/ASR-Report-yellow?logo=arxiv)](https://arxiv.org/pdf/2601.18184)
[![Colab](https://img.shields.io/badge/StreamingTTS-Colab-green?logo=googlecolab)](https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/VibeVoice_colab.ipynb)
[![ASR Playground](https://img.shields.io/badge/ASR-Playground-6F42C1?logo=gradio)](https://aka.ms/vibevoice-asr)

[![microsoft%2FVibeVoice | Trendshift](https://trendshift.io/api/badge/repositories/15465)](https://trendshift.io/repositories/15465)

</div>


<div align="center">
<picture>
  <source media="(prefers-color-scheme: dark)" srcset="Figures/VibeVoice_logo_white.png">
  <img src="Figures/VibeVoice_logo.png" alt="VibeVoice Logo" width="300">
</picture>
</div>

<div align="left">

<h3>📰 News</h3>

<strong>2026-09-03: 🚀 We released <a href="https://github.com/microsoft/VibeVoice/blob/main/docs/vibevoice-asr-streaming.md">VibeVoice-ASR-Streaming</a>, a unified streaming ASR model that continuously transcribes ''who said what'' as speech arrives, with support for customized hotwords and 10 languages. [<a href="https://aka.ms/vibeasr">Demo</a>] [<a href="https://huggingface.co/microsoft/VibeVoice-ASR-Streaming-7B">Models</a>] [<a href="https://arxiv.org/abs/2609.02812">Report</a>]</strong>

<strong>2026-07-23: ⚡ We released <a href="https://github.com/microsoft/VibeASR.cpp">VibeVoice-ASR-BitNet</a>, an edge CPU inference engine for VibeVoice-ASR. Through heterogeneous quantization (I8_S + I2_S), the model is compressed from 4.62 GB to 1.58 GB with real-time inference (RTF < 1) on 3+ CPU threads — no GPU required. [<a href="https://github.com/microsoft/VibeASR.cpp">Code</a>] [<a href="https://huggingface.co/microsoft/VibeVoice-ASR-BitNet">Models</a>] [<a href="https://arxiv.org/abs/2607.21075">Report</a>]</strong>

<strong>2026-03-12: 🚀 VibeVoice-ASR is now integrated into <a href="https://labs.ai.azure.com/innovations/vibevoice-asr/">Azure AI Foundry Labs</a>! You can now explore and test our unified speech-to-text capabilities directly through Microsoft Foundry.</strong>

<strong>2026-03-06: 🚀 VibeVoice ASR is now part of a <a href="https://huggingface.co/microsoft/VibeVoice-ASR-HF">Transformers release</a>! You can now use our speech recognition model directly through the Hugging Face Transformers library for seamless integration into your projects.</strong>

<strong>2026-01-21:</strong> 📣 We open-sourced <a href="docs/vibevoice-asr.md"><strong>VibeVoice-ASR</strong></a>, a unified sp