Mark Zuckerberg(@finkd):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.

2026.09.01 17:15

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.

395

5.5K

471

Forward to community

Most Popular Users

1M Followers

957.3K Followers

1.1M Followers

578.9K Followers

504.5K Followers

6.3M Followers

347.3K Followers

2.8M Followers

The Wall Street Journal

22.3M Followers

672.4K Followers

1.2M Followers

4.3M Followers

2.7M Followers

26.4M Followers

241M Followers