Scale AI Releases Muse Voice Transcribe: SOTA Real-Time Speech-to-Text Model

rohanpaul_ai · x · 2026-09-02

Scale AI has released Muse Voice Transcribe, its first real-time audio perception model. The model achieves state-of-the-art performance in streaming speech-to-text and natively handles speaker diarization and endpointing within a single model.

Related event: Meta Launches Muse Voice Transcribe, Claiming SOTA Streaming ASR(10 posts)→

Original post →

More from Models

Models channel →