--- title: Intelligent transcription with Gemini 3.5 Transcribe description: Google introduces Gemini 3.5 Transcribe, a new speech-to-text model available via the Live API (streaming) and Interactions API (pre-recorded audio). It offers... canonical: https://daily.dev/posts/intelligent-transcription-with-gemini-3-5-transcribe-poly4ngnn twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Intelligent transcription with Gemini 3.5 Transcribe | daily.dev og:description: Google introduces Gemini 3.5 Transcribe, a new speech-to-text model available via the Live API (streaming) and Interactions API (pre-recorded audio). It offers... og:url: https://daily.dev/posts/intelligent-transcription-with-gemini-3-5-transcribe-poly4ngnn og:image: https://api.daily.dev/og/posts/POLY4NgNn.png og:image:alt: Intelligent transcription with Gemini 3.5 Transcribe 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. # Intelligent transcription with Gemini 3.5 Transcribe **[DeepMind](https://daily.dev/sources/dm)** · 5 min read · 0 upvotes · 0 comments ## Summary Google introduces Gemini 3.5 Transcribe, a new speech-to-text model available via the Live API (streaming) and Interactions API (pre-recorded audio). It offers self-correction handling, filler-word removal, custom vocabulary support, speaker attribution, and over 85 languages. Compared to the previous Chirp 3 model, it achieves lower word error rates (4.0% streaming, 2.6% non-streaming per Artificial Analysis) and 70% faster time-to-final-transcription. It's rolling out in Google AI Studio, Gemini Enterprise Agent Platform, Gboard's Rambler feature, Google Antigravity, the Gemini app on macOS, and soon Chrome, with third-party platforms like LiveKit, Pipecat, and Vercel already integrating it. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Gemini 3.5 Transcribe and how does it differ from Chirp 3? Gemini 3.5 Transcribe is Google's newest speech-to-text model, designed for intelligent voice interactions with self-correction handling, filler-word removal, and auto-formatting. Compared to the previous Chirp 3 model, it improves word error rate and, per Artificial Analysis measurements, cuts time to final transcription by 70%, offering significantly better latency and accuracy. _Developers evaluating speech-to-text upgrades can track releases like this one on daily.dev._ ### What word error rate does Gemini 3.5 Transcribe achieve for streaming versus pre-recorded audio? According to Artificial Analysis measurements, Gemini 3.5 Transcribe achieves a 4.0% word error rate for streaming transcription and 2.6% for non-streaming, pre-recorded use cases. On the FLEURS multilingual benchmark it reaches 5.50% WER in streaming mode and 5.04% WER in non-streaming mode across a set of top languages and locales. _Teams comparing transcription model accuracy can follow benchmark updates like these on daily.dev._ ### Which APIs give developers access to Gemini 3.5 Transcribe and what do they support? Two separate APIs expose the model: the Live API offers real-time, bidirectional streaming with sub-second latency using gemini-3.5-transcribe-live, while the Interactions API handles pre-recorded audio, meetings, and call logs with speaker attribution and word-level timestamps using gemini-3.5-transcribe. Both are in public preview through Google AI Studio and Gemini Enterprise Agent Platform. _Developers building voice agents can keep up with API options like these via daily.dev._ ## Similar posts on daily.dev - [Fluid, natural voice translation with Gemini 3.5 Live Translate](https://daily.dev/posts/fluid-natural-voice-translation-with-gemini-3-5-live-translate-egnwzzctw) · DeepMind · 0 upvotes · 0 comments - [Trying out Gemini 3 Pro with audio transcription and a new pelican benchmark](https://daily.dev/posts/trying-out-gemini-3-pro-with-audio-transcription-and-a-new-pelican-benchmark-6ratpcshl) · Hacker News · 0 upvotes · 0 comments - [Gemini 3.1 Flash TTS on Google Cloud](https://daily.dev/posts/gemini-3-1-flash-tts-on-google-cloud-pl4nonfnc) · Google Cloud · 0 upvotes · 0 comments --- Tags: [#google](https://daily.dev/tags/google), [#google-gemini](https://daily.dev/tags/google-gemini), [#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/intelligent-transcription-with-gemini-3-5-transcribe-poly4ngnn) ```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":"Intelligent transcription with Gemini 3.5 Transcribe","url":"https://daily.dev/posts/intelligent-transcription-with-gemini-3-5-transcribe-poly4ngnn","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/intelligent-transcription-with-gemini-3-5-transcribe-poly4ngnn"},"datePublished":"2026-08-26T17:21:02.683Z","dateModified":"2026-09-14T09:34:22.730Z","description":"Google introduces Gemini 3.5 Transcribe, a new speech-to-text model available via the Live API (streaming) and Interactions API (pre-recorded audio). It offers...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/57ca82980b7b1524508eaba413ca9a16?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/57ca82980b7b1524508eaba413ca9a16?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"DeepMind","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":"DeepMind","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/dm","url":"https://daily.dev/sources/dm"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/intelligent-transcription-with-gemini-3-5-transcribe-poly4ngnn","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"google,google-gemini,speech-recognition,voice-ai","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"DeepMind","item":"https://daily.dev/sources/dm"},{"@type":"ListItem","position":3,"name":"Intelligent transcription with Gemini 3.5 Transcribe"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/intelligent-transcription-with-gemini-3-5-transcribe-poly4ngnn#faq","mainEntity":[{"@type":"Question","name":"What is Gemini 3.5 Transcribe and how does it differ from Chirp 3?","acceptedAnswer":{"@type":"Answer","text":"Gemini 3.5 Transcribe is Google's newest speech-to-text model, designed for intelligent voice interactions with self-correction handling, filler-word removal, and auto-formatting. Compared to the previous Chirp 3 model, it improves word error rate and, per Artificial Analysis measurements, cuts time to final transcription by 70%, offering significantly better latency and accuracy. Developers evaluating speech-to-text upgrades can track releases like this one on daily.dev."}},{"@type":"Question","name":"What word error rate does Gemini 3.5 Transcribe achieve for streaming versus pre-recorded audio?","acceptedAnswer":{"@type":"Answer","text":"According to Artificial Analysis measurements, Gemini 3.5 Transcribe achieves a 4.0% word error rate for streaming transcription and 2.6% for non-streaming, pre-recorded use cases. On the FLEURS multilingual benchmark it reaches 5.50% WER in streaming mode and 5.04% WER in non-streaming mode across a set of top languages and locales. Teams comparing transcription model accuracy can follow benchmark updates like these on daily.dev."}},{"@type":"Question","name":"Which APIs give developers access to Gemini 3.5 Transcribe and what do they support?","acceptedAnswer":{"@type":"Answer","text":"Two separate APIs expose the model: the Live API offers real-time, bidirectional streaming with sub-second latency using gemini-3.5-transcribe-live, while the Interactions API handles pre-recorded audio, meetings, and call logs with speaker attribution and word-level timestamps using gemini-3.5-transcribe. Both are in public preview through Google AI Studio and Gemini Enterprise Agent Platform. Developers building voice agents can keep up with API options like these via daily.dev."}}]} ```