---
id: "b900"
language: "en"
library: "tools"
official_url: "https://github.com/microsoft/VibeVoice"
profile_updated_on: "2026-10-20"
---

# VibeVoice

Use ASR checkpoints for transcripts, timestamps and speaker segments, or a separate Realtime model for streaming English single-speaker TTS.

- Company / organization: Microsoft Corporation
- Company country / region: United States · Published company address
- Category: Speech recognition & input
- Official website: [https://github.com/microsoft/VibeVoice](https://github.com/microsoft/VibeVoice)
- Profile updated: 2026-10-20


## Overview

VibeVoice contains task-specific speech models. ASR takes long recordings and hotword context to jointly return text, timestamps and speaker segments; ASR-Streaming emits text as audio chunks arrive. Realtime-0.5B is a separate English single-speaker TTS model using prepared voice prompts, not the same capability set as long-form multi-speaker models. Official inference and serving examples are available. Reviewed ASR and Realtime cards declare MIT; scope remains model-specific.

## Access options

### Visit website · Speech recognition & input

Use ASR checkpoints for transcripts, timestamps and speaker segments, or a separate Realtime model for streaming English single-speaker TTS.

[Visit website](https://github.com/microsoft/VibeVoice)

## Official sources and references

- [Official website](https://github.com/microsoft/VibeVoice)
- [Documentation](https://github.com/microsoft/VibeVoice/blob/main/docs/vibevoice-asr.md)
- [Documentation](https://github.com/microsoft/VibeVoice/blob/main/docs/vibevoice-asr-streaming.md)
- [Documentation](https://github.com/microsoft/VibeVoice/blob/main/docs/vibevoice-realtime-0.5b.md)

## Reading & subscriptions

- [Interactive profile](../../../products/vibevoice--b900.html)
- [Read](../../../read/en/products/vibevoice--b900.html)
- [JSON](../../../read/en/products/vibevoice--b900.json)

Descriptions summarize public information; consult official websites for features, pricing and regional availability.