Meta Launches Muse Voice Transcribe

Meta Superintelligence Labs has released Muse Voice Transcribe, a real-time speech recognition model capable of distinguishing between more than 20 speakers. The system supports over 70 languages, handles mid-sentence code-switching, and utilizes an adaptive delay mechanism to balance transcription speed and accuracy.

The model is available through the Meta Model API, Meta AI for Mac, and Muse Code. API pricing is set at $0.18 per hour.