Meta Releases Muse Voice: Real-Time Audio Transcription for 70+ Languages

alexandr_wang · x · 2026-09-02

Meta has introduced Muse Voice Transcribe, its first real-time audio perception model. It supports real-time transcription in over 70 languages and features diarization capable of distinguishing between more than 20 speakers. The feature is now available in the Meta AI macOS app.

Related event: Meta Launches Muse Voice Transcribe, Claiming SOTA Streaming Speech-to-Text(17 posts)→

Original post →

More from Multimodal

Multimodal channel →