Meta Launches Muse Voice Transcribe: Streaming STT With 3.1% Word Error Rate
rohanpaul_ai · x · 2026-09-02
Meta has shipped Muse Voice Transcribe, MSL's first real-time audio perception model, announced by finkd:
- 3.1% final-transcription word error rate with adaptive delay, claimed significantly ahead of competitors.
- Beyond transcription: a single streaming model natively handles speaker diarization and endpointing — learning when to wait, commit a word, or end a turn.
- Audio is processed in 80ms chunks, deciding per chunk whether to emit text or keep listening, positioning it as a real-time perception layer for voice agents.
- Available via Meta Model API, Meta AI for Mac, and Muse Code.
More from Multimodal
- Apple's immersive horror short Remnants wows Vision Pro users with 3D presence — Scobleizer · 2026-10-18
- H3 360° Orbit Camera LoRA for MiniMax Open-Sourced, Generates Smooth 5.2s Shots — merica420_69 · 2026-10-18
- 'Tesla in Pakistan' AI video made with Seedance 2.5 goes viral — SimplyAnnisa · 2026-10-18
- Borges's nine stories turned into walkable 3D worlds with AI model Fable 5.1 — emollick · 2026-10-18
- Midjourney cozy couple photo: full prompt shared for killing the AI plastic look — tisch_eins · 2026-10-18
- Higgsfield playbook: scene templates, paid creator network, $20-to-enterprise funnel — sujingshen · 2026-10-18