Meta Launches Muse Voice Transcribe Real-Time Model
Meta Superintelligence Labs releases its first real-time audio perception model for streaming speech.
Mark Zuckerberg announced Muse Voice Transcribe as Meta Superintelligence Labs' first real-time audio perception model. The system performs streaming speech-to-text, diarization, and endpointing in one model. It uses adaptive delay to balance speed and accuracy. The model supports multiple languages with code-switching. It now powers dictation in the Meta desktop app and voice input in Muse Code. Access is live through the Meta Model API, Meta AI for Mac, and Muse Code, including a zero-data-retention tier on the API. The official research blog post confirms the rollout.
Muse Voice Transcribe is MSL's first real-time audio perception model -- rolling out today. SOTA in streaming speech-to-text, it handles speaker diarization, and endpointing natively in a single model.
Meta Launches Muse Voice Transcribe Real-Time Model
Meta Superintelligence Labs releases its first real-time audio perception model for streaming speech.
Reactions
6 postsMZ 
Mark Zuckerberg@finkdThe model decides when to listen. It waits a little longer on hard words and commits faster on easy ones, using adaptive delay to predict each token and increase accuracy. With adaptive delay, the model is near the pareto front on speed-accuracy tradeoff.
- likes: 413
- replies: 29
- bookmarks: 13
- reposts: 19
MZ Mark Zuckerberg@finkdAlready powering dictation in the Meta desktop app and voice input in Muse Code. Live now on the Meta model API with a zero-data-retention tier.
- likes: 263
- replies: 19
- bookmarks: 74
- reposts: 19
AV Alex Volkov@altryne@finkd let's go! Just a week after Gemini 3.5 intelligence transcribe models! WIll put them to the test on @thursdai_pod 🫡 this week!
- likes: 3
- replies: 1
- bookmarks: 0
- reposts: 0
AA AI at Meta@AIatMetaIntroducing Muse Voice Transcribe, the first real-time audio perception model from Meta Superintelligence Labs. Muse Voice Transcribe delivers real-time streaming ASR, diarization with 20+ speakers, and endpointing. It’s multilingual with seamless code-switching and improves…
- likes: 1K
- replies: 41
- bookmarks: 338
- reposts: 131
AA AI at Meta@AIatMetaMuse Voice Transcribe is available today via Meta Model API, Meta AI for Mac, and Muse Code. Learn more: https://go.meta.me/4xISnl2
- likes: 31
- replies: 1
- bookmarks: 8
- reposts: 3
RP Rohan Paul@rohanpaul_ai@finkd wow, Meta is on fire. Congrats Mark. looks like a brilliant model.
- likes: 16
- replies: 1
- bookmarks: 0
- reposts: 0
