Meta's new AI transcription model can distinguish between multiple speakers and languages in real-time

The latest release from Meta Superintelligence Lab is a powerful transcription model. Meta’s new AI transcription model can distinguish between multiple speakers and languages in real-time. The model can handle dictation and transcription for more than 20 speakers and can smoothly handle multiple languages at once, Meta says.

Meta CEO Mark Zuckerberg, who recently returned to X after three years of not posting on the platform, shared an example of the model’s ability to handle multiple speakers and languages at once. In the video, the transcription is able to automatically distinguish between multiple speakers and switch between languages. It’s even able to pick up on "code-switching" and transcribe sentences that use words from multiple languages.

Muse Voice Transcribe is MSL’s first real-time audio perception model — rolling out today. SOTA in streaming speech-to-text, it handles speaker diarization, and endpointing natively in a single model. Pic.twitter.com/LViMDSkbim — Mark Zuckerberg (@finkd) September 1, 2026 "The model decides when to listen.

It brings multilingual, streaming transcription to Meta AI for Mac, Muse Code, and developers through the Meta Model API. Meta launches Muse Voice Transcribe for real-time voice dictation on Mac.

Read John Ternus’s full memo to Apple employees on his first day as CEO Chance Miller Sep 1 2026.