--- title: Meta's Muse Voice Transcribe: a real-time speech model... description: Meta's AI research lab released Muse Voice Transcribe, a real-time audio perception model that combines transcription, speaker diarization, and endpointing... canonical: https://daily.dev/posts/meta-s-muse-voice-transcribe-a-real-time-speech-model-that-handles-transcription-diarization-and--y3qwttey5 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Meta's Muse Voice Transcribe: a real-time speech model that handles transcription, diarization, and endpointing in one pass | daily.dev og:description: Meta's AI research lab released Muse Voice Transcribe, a real-time audio perception model that combines transcription, speaker diarization, and endpointing... og:url: https://daily.dev/posts/meta-s-muse-voice-transcribe-a-real-time-speech-model-that-handles-transcription-diarization-and--y3qwttey5 og:image: https://api.daily.dev/og/posts/Y3QwTTEy5.png og:image:alt: Meta's Muse Voice Transcribe: a real-time speech model that handles transcription, diarization, and endpointing in one pass og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Meta's Muse Voice Transcribe: a real-time speech model that handles transcription, diarization, and endpointing in one pass **[Collections](https://daily.dev/sources/collections)** · 1 min read · 0 upvotes · 0 comments ## Summary Meta's AI research lab released Muse Voice Transcribe, a real-time audio perception model that combines transcription, speaker diarization, and endpointing into a single pass rather than stitching together separate models. It processes audio in 80ms chunks, deciding after each chunk whether to emit text or keep listening, achieving a 3.1% final-transcription word error rate with adaptive delay that beats competing streaming speech-to-text models. It's positioned as a perception layer for voice agents and is available via the Meta Model API, Meta AI for Mac, and Muse Code. ## Content Meta's Superintelligence Labs just released Muse Voice Transcribe, their first real-time audio perception model, and it's sitting at the top of the AA-WER Streaming benchmark with a 3.1% final-transcription word error rate. That puts it ahead of Cartesia Ink-2, ElevenLabs Scribe v2 Realtime, GPT Live Transcribe, and Gemini 3.5 Transcribe Live. What makes it interesting isn't just the accuracy number. The model processes audio in 80ms chunks and decides after each one whether to emit text or keep listening. That decision - when to wait, when to commit a word, when a speaker has changed, when a turn is actually over - is all handled inside a single streaming model, learned through reinforcement learning. Most speech-to-text systems bolt these things on separately. Muse does it natively. Other specs worth noting: - Distinguishes over 20 speakers (diarization built in) - Supports 70+ languages with mid-conversation language switching - Handles hour-long conversations It's available through the Meta Model API, Meta AI for Mac, and Muse Code, priced at $3.00 per 1,000 audio-minutes. One thing to flag: unlike Meta's Llama models, the weights won't be open-sourced. ## Questions this post answers ### What is Meta's Muse Voice Transcribe model and how does it differ from a standard speech-to-text API? Muse Voice Transcribe is Meta's first real-time audio perception model, handling transcription, speaker diarization, and endpointing within a single model rather than as separate post-processing stages. It processes audio in 80ms chunks and decides after each chunk whether to emit text or keep listening, achieving a 3.1% final-transcription word error rate with adaptive delay, ahead of competing streaming speech-to-text models. _Teams building voice agents can track new speech-model releases like this on daily.dev._ ### Where can I access Meta's Muse Voice Transcribe model? It is available through the Meta Model API, Meta AI for Mac, and Muse Code. It functions as a perception layer suited for voice agents, since it combines transcription, diarization, and endpointing in one pass instead of requiring multiple stitched-together models. _Developers evaluating voice-agent tooling can follow access changes for models like this on daily.dev._ ## Community take How the wider developer community reacted, aggregated from 3 discussions and 217 comments across x (as of 2026-09-02). **TL;DR:** Reaction is largely enthusiastic about combining streaming transcription, diarization, and turn-detection into one model, with people excited for Meta glasses and dictation use cases, though pricing structure, availability, and the lack of open weights draw some pushback. **Sentiment:** 58% positive · 25% mixed · 17% skeptical **The case for** - Unifying diarization, transcription, and turn-end detection into a single streaming model is seen as a genuine technical advance over janky post-processing pipelines. - The quoted per-minute pricing is viewed as reasonable if quality matches the demo. - People are excited about applications like meeting notes, dictation, and integration with wearable devices. **The pushback** - Some argue the weights not being open-sourced is a letdown given Meta's usual open approach with Llama. - Availability is limited in some regions, frustrating people who want to try it. - Skepticism exists about real-world robustness with noisy environments, overlapping speakers, and code-switching between languages/accents that the demo doesn't fully address. - A few doubt adoption or think Meta is late compared to competitors already doing real-time streaming and diarization. **By community** - x (positive): Replies skew celebratory about the technical unification of streaming ASR, diarization, and turn detection, with pricing seen as fair, though mixed in with off-topic noise, spam, and a few skeptical or unrelated political tangents. **Hottest debate:** Whether Meta withholding open weights for this model (unlike Llama) is a disappointing step back or an understandable business choice. **Open questions** - How well does the model handle heavy accents, regional languages, and mid-sentence code-switching in practice, e.g., Hindi/English or African accents? - How does streaming pricing/cost structure compare to batch transcription given the model holds a GPU open for live calls? - Will the model ever be open-sourced or made available on-device? - Does it provide persistent unique speaker embeddings across sessions rather than just per-conversation speaker indices? **Highlights** > @finkd Streaming STT with native diarization in one model is nuts. Diarization post-processing is always the janky part. > — [websterweby on x · 1 points](https://x.com/websterweby/status/2094837161954811958) > @finkd SOTA streaming STT with native diarization and adaptive delay is a serious flex well done. > — [examaddaorg on x · 1 points](https://x.com/examaddaorg/status/2094842355061002663) > @finkd 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 > — [full\_kelly\_ on x](https://x.com/full_kelly_/status/2094841343726034978) > @finkd Does it return unique embedding for the speaker? If not it’s useless as we can’t dereference against known users. Cc @ElevenLabsDevs @DeepgramAI first one to give me unique IDs - not indexes in the thread - takes the money. > — [PietroCasella on x · 1 comments](https://x.com/PietroCasella/status/2094857830197067940) > @finkd 70+ languages is impressive, but the mid sentence code switching is the part I’m most curious about. How well does it handle Indian users switching between Hindi/English and regional languages in the same sentence? > — [STORYTELLER8987 on x](https://x.com/STORYTELLER8987/status/2094838171054030928) **Source threads** - [x](https://x.com/finkd/status/2094836602681938385) · 0 points · 216 comments - [x](https://x.com/rohanpaul_ai/status/2094843121658216896) · 0 points · 1 comments - [x](https://x.com/giffmana/status/2094846863878848919) · 0 points · 0 comments ## Similar posts on daily.dev - [Meta enters the crowded AI coding battle with Muse Spark 1.1](https://daily.dev/posts/meta-enters-the-crowded-ai-coding-battle-with-muse-spark-1-1-wtfjrleyt) · TechCrunch · 1 upvotes · 0 comments - [OpenAI launches GPT-Realtime-2 and two new voice API models](https://daily.dev/posts/openai-launches-gpt-realtime-2-and-two-new-voice-api-models-aedadynny) · The Next Web · 3 upvotes · 0 comments --- Tags: [#speech-recognition](https://daily.dev/tags/speech-recognition), [#voice-ai](https://daily.dev/tags/voice-ai) [View this post on daily.dev](https://daily.dev/posts/meta-s-muse-voice-transcribe-a-real-time-speech-model-that-handles-transcription-diarization-and--y3qwttey5) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Meta's Muse Voice Transcribe: a real-time speech model that handles transcription, diarization, and endpointing in one pass","url":"https://daily.dev/posts/meta-s-muse-voice-transcribe-a-real-time-speech-model-that-handles-transcription-diarization-and--y3qwttey5","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/meta-s-muse-voice-transcribe-a-real-time-speech-model-that-handles-transcription-diarization-and--y3qwttey5"},"datePublished":"2026-09-01T17:42:04.923Z","dateModified":"2026-09-02T12:20:07.755Z","description":"Meta's AI research lab released Muse Voice Transcribe, a real-time audio perception model that combines transcription, speaker diarization, and endpointing...","image":"https://pbs.twimg.com/media/HRJftxla4AARaf7.jpg","thumbnailUrl":"https://pbs.twimg.com/media/HRJftxla4AARaf7.jpg","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/meta-s-muse-voice-transcribe-a-real-time-speech-model-that-handles-transcription-diarization-and--y3qwttey5","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"speech-recognition,voice-ai","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"Meta's Muse Voice Transcribe: a real-time speech model that handles transcription, diarization, and endpointing in one pass"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/meta-s-muse-voice-transcribe-a-real-time-speech-model-that-handles-transcription-diarization-and--y3qwttey5#faq","mainEntity":[{"@type":"Question","name":"What is Meta's Muse Voice Transcribe model and how does it differ from a standard speech-to-text API?","acceptedAnswer":{"@type":"Answer","text":"Muse Voice Transcribe is Meta's first real-time audio perception model, handling transcription, speaker diarization, and endpointing within a single model rather than as separate post-processing stages. It processes audio in 80ms chunks and decides after each chunk whether to emit text or keep listening, achieving a 3.1% final-transcription word error rate with adaptive delay, ahead of competing streaming speech-to-text models. Teams building voice agents can track new speech-model releases like this on daily.dev."}},{"@type":"Question","name":"Where can I access Meta's Muse Voice Transcribe model?","acceptedAnswer":{"@type":"Answer","text":"It is available through the Meta Model API, Meta AI for Mac, and Muse Code. It functions as a perception layer suited for voice agents, since it combines transcription, diarization, and endpointing in one pass instead of requiring multiple stitched-together models. Developers evaluating voice-agent tooling can follow access changes for models like this on daily.dev."}}]} ```