Meta CEO Zuckerberg announces Muse Voice Transcribe real-time audio model

Meta CEO Mark Zuckerberg announced the launch of Muse Voice Transcribe, described as the company's first real-time audio perception model. The model handles speech-to-text, speaker diarization, and endpointing natively in a single model, and is claimed to be state-of-the-art in streaming speech-to-text. The rollout begins today.