Meta Superintelligence Labs releases Muse Voice Transcribe real-time speech model
Introducing Muse Voice Transcribe
Meta Superintelligence Labs introduced Muse Voice Transcribe, its first real-time audio perception model, which performs streaming ASR, diarization for 20+ speakers and endpointing. The autoregressive model from the Muse Spark family processes audio in 80ms chunks and uses reinforcement learning to adaptively trade accuracy against delay, and it was trained on 70+ languages with 25 extensively verified. Meta says it ranks first on Artificial Analysis for streaming speech-to-text and on public diarization benchmarks, as of September 1, 2026.
Meta Superintelligence Labs details how its first real-time audio perception model handles streaming ASR, 20+ speaker diarization and code-switching, with token-level design choices worth studying.
Source:Meta AI Research Blog · research.meta.ai