LaunchAI ModelsSeptember 2, 2026

Meta Superintelligence Labs releases Muse Voice Transcribe

Muse Voice Transcribe is Meta's first real-time audio perception model, combining streaming speech-to-text, endpointing, and diarization for 20+ speakers in one model. It tops AA-WER Streaming final transcript accuracy at 3.1% WER, 0.16s after end of speech, and is priced at $0.18 per hour.

How this story unfolded

1 day · 3 reports · 5 community posts · from Sep 1

  1. Sep 1
  2. Sep 2

More stories today

Open the live feed