Muse Voice Transcribe is MSL's first real-time audio perception model -- rolling out today.
@finkd2.5M followers
1,130,187 views
36 Comments
Comments from the original post on X (Twitter)

@finkd
The 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.
664 likes

@finkd
It holds up on messy, real audio too -- trained across 70+ languages (with 25 validated at launch), handles mid-sentence code-switching, and manages hour-long sessions with 20+ speakers. You can bias it toward names and domain terms as well.
387 likes

@finkd
Already 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.
354 likes

@andimarafioti
@eliza_luth
113 likes

@rohanpaul_ai
wow, Meta is on fire. Congrats Mark. looks like a brilliant model.
21 likes

@DiligentPlane
mark is in grind mode rn Love to see it
13 likes

@hbredin
Rule of thumb: If @pyannoteAI is missing from the benchmark, there's probably a reason. cc @finkd @AIatMeta @alex_conneau
12 likes

@logarithmatic
Nice work; it seems there are a lot of American researchers there.
11 likes

@Abhishocked
Nice to see so many releases from meta. Always rooting for meta. Btw What is the cost to transcribe an hour video? I have here explained why 0.1 usd per hour or less is the right price for transcription.
9 likes

@Maksim_P_M
Going to be amazing for the meta glasses
6 likes

@full_kelly_
Incredible performance that blows the existing SOTA at detecting voices out of the water, but it's a shame you're not releasing an open weights model version
4 likes

@foodchef247
Is social media Algorithms now run by medieval dictators? Does your followers read your posts & replies? - ELQUOR
4 likes

@AlloraNetwork
The next constraint is still judgment. Once systems can hear continuously, they need intelligence that stays accurate as conditions change, not just a better transcript.
4 likes

@altryne
let's go! Just a week after Gemini 3.5 intelligence transcribe models! WIll put them to the test on @thursdai_pod 🫡 this week!
4 likes

@elshayib_
Bro no one cares Fable 5.1 around the corner fuck that
3 likes

@freemanjiangg
Would love to see how this performs on
3 likes

@ivanfioravanti
Great release! Keep pushing!
3 likes

@utkuagi
Congrats!
3 likes

@Jim_Faster
Looks absolutely incredible. I wish it was open source but I understand this is a lot of work.
3 likes

@examaddaorg
SOTA streaming STT with native diarization and adaptive delay is a serious flex well done.
3 likes















