Meta Superintelligence Labs releases Muse Voice Transcribe

Meta Superintelligence Labs released Muse Voice Transcribe, its first real-time audio perception model that unifies streaming ASR, speaker diarization for 20+ speakers, and endpointing in a single autoregressive system. The model supports 25+ validated languages with seamless code-switching and adaptive delay. It ranked first on Artificial Analysis streaming speech-to-text and public diarization benchmarks as of the launch date and is available via the Meta Model API.