Meta Superintelligence Labs launches Muse Voice Transcribe real-time speech model
Start here
Meta Superintelligence Labs released Muse Voice Transcribe, its first real-time audio perception model. It performs streaming speech recognition, speaker diarization for more than 20 speakers and endpointing, processing audio in 80ms chunks; Meta says reinforcement learning lets it trade accuracy against delay adaptively. The model was trained on more than 70 languages, with 25 extensively verified ones recommended for the initial release; other languages are also supported. Meta says it ranks first on Artificial Analysis for streaming speech-to-text and on public diarization benchmarks, as of September 1, 2026.
Generated from reports · updated 3 h ago
Report timeline
Follow the reports to see the event from different sides.
- Meta AI Research BlogPicksMeta Superintelligence Labs releases Muse Voice Transcribe real-time speech model
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.
Heat for this event
- Current, comparable range
- 9
- Peak, comparable range
- 10November 16 13:00
- Change in 24 hours
- –
The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.