Meta Introduces Muse Voice Transcribe for Real-Time Speech-to-Text with 20+ Speaker Diarization

Summary

Meta has launched Muse Voice Transcribe, a new real-time speech-to-text model offering transcription, endpoint detection, and diarization for over 20 speakers at $0.18 per hour. Developed by Meta Superintelligence Labs, the model supports long audio, multilingual code-switching, and integrates speaker attribution directly into its architecture.