Overview
A real-time audio perception model in the Muse family for streaming speech recognition, diarization, endpointing, and multilingual mixed speech.
Muse Voice Transcribe
A real-time audio perception model in the Muse family for streaming speech recognition, diarization, endpointing, and multilingual mixed speech.
MODEL NUMBER108
- Release date
- 2026-09-01
- Organization
- Meta
- Family
- Muse
01
Specifications
Only published specifications are shown.
02
Overview
Why it mattered
It extends Muse beyond multimodal reasoning into real-time voice input, supporting audio longer than an hour and more than 20 speakers.
03
Architecture & capabilities
Key capabilities
audio transcriptiondiarizationendpointingMultilingualLong context
04
Release history
Muse Voice Transcribe launched in Meta Model API, Meta AI for Mac, and Muse Code.
View source05
Related models
Select a card to view the related model.
No related models recorded yet
06