MSL Releases Muse Voice: SOTA Real-Time Transcription Model

bowenc0221 · x · 2026-09-02

MSL has launched Muse Voice Transcribe, its first real-time audio perception model. It achieves SOTA performance in streaming speech-to-text, natively handles speaker diarization and endpointing, and is available via API.

Related event: Meta Launches Muse Voice Transcribe, Its First Real-Time Audio Perception Model(11 posts)→

Original post →

More from Models

Models channel →