Meta Superintelligence Labs this week introduced Muse Voice Transcribe, a real-time audio perception model that combines streaming automatic speech recognition, speaker diarization for more than 20 people, and endpoint detection in a single autoregressive system without post-processing. The model is now available as a hosted API through the Meta Model API, priced at $3 per 1,000 audio minutes, and already supports dictation features in Meta AI for Mac and Muse Code.
According to the release cited by MarkTechPost, Muse Voice Transcribe was trained on more than 70 languages, with 25 languages broadly validated and recommended at launch. Meta said the model natively handles audio inputs longer than one hour and supports more than 20 speakers without requiring post-processing steps. The company also reported that, as of Sept. 1, 2026, the model ranked first on Artificial Analysis benchmarks for streaming speech-to-text and public speaker diarization.
Meta Superintelligence Labs this week released Muse Voice Transcribe, a real-time audio perception model.
The model combines three tasks in one autoregressive system: streaming automatic speech recognition, speaker diarization for more than 20 people, and endpoint detection. Meta said it does not require post-processing. Muse Voice Transcribe is now available as a hosted API on the Meta Model API at $3 per 1,000 audio minutes, and it already powers dictation features in Meta AI for Mac and Muse Code.
Meta said the model was trained on more than 70 languages, with 25 of them extensively validated and recommended at launch. It natively supports audio inputs longer than one hour and more than 20 speakers, also without post-processing steps.
According to Meta, as of Sept. 1, 2026, Muse Voice Transcribe ranked first in Artificial Analysis benchmarks for streaming speech-to-text and public speaker diarization. The update was cited by MarkTechPost.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
