--- title: How to build with Gemini 3.5 Transcribe | daily.dev description: Google introduces Gemini 3.5 Transcribe, its first Gemini-based transcription model, available both for batch use on the Interactions API and real-time use on... canonical: https://daily.dev/posts/how-to-build-with-gemini-3-5-transcribe-q6cozyqbn twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How to build with Gemini 3.5 Transcribe | daily.dev og:description: Google introduces Gemini 3.5 Transcribe, its first Gemini-based transcription model, available both for batch use on the Interactions API and real-time use on... og:url: https://daily.dev/posts/how-to-build-with-gemini-3-5-transcribe-q6cozyqbn og:image: https://api.daily.dev/og/posts/Q6COzYQbn.png og:image:alt: How to build 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. # How to build with Gemini 3.5 Transcribe **[Google for Developers](https://daily.dev/sources/googledevelopers)** · 4 min read · 0 upvotes · 0 comments ## Summary Google introduces Gemini 3.5 Transcribe, its first Gemini-based transcription model, available both for batch use on the Interactions API and real-time use on the Live API. Being LLM-based, it handles tricky content like alphanumeric strings, email addresses, phone numbers, and unit conversions better than traditional transcription models, and supports custom vocabulary and language hints to boost accuracy for names and terms. It automatically recognizes over 70 languages even when only English hints are set, and can intelligently correct itself mid-transcript, such as fixing a misheard email address. ## 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 is it different from traditional transcription models? Gemini 3.5 Transcribe is Google's first Gemini-based transcription model, available for batch transcription on the Interactions API and real-time transcription on the Live API. Because it is LLM-based rather than a traditional acoustic model, it handles alphanumeric strings, email addresses, and phone numbers more accurately, supports custom vocabulary and language hints, and can self-correct mistakes mid-transcript. _Developers evaluating transcription APIs can follow Gemini's evolving capabilities on daily.dev._ ### Does Gemini 3.5 Transcribe support languages other than the one specified in language hints? Yes, Gemini 3.5 Transcribe can recognize and transcribe over 70 languages automatically even when language hints are set to only English. Setting language hints or codes still improves transcription accuracy, but the model's underlying audio understanding allows it to detect and correctly transcribe mixed-language speech, such as English mixed with German number terms. _Teams building multilingual voice apps can track transcription model updates like this on daily.dev._ ### Can Gemini 3.5 Transcribe correctly format spoken email addresses and phone numbers? Yes, Gemini 3.5 Transcribe can correctly format spoken email addresses, such as converting a spelled-out address into the proper 'name@google.com' format, and it recognizes phone number formats across regions, including US ten-digit numbers and Singapore's eight-digit numbers, correcting itself if an initial guess was wrong. _Anyone integrating voice input into forms can watch for accuracy gains like this on daily.dev._ --- Tags: [#google](https://daily.dev/tags/google), [#llm](https://daily.dev/tags/llm), [#google-gemini](https://daily.dev/tags/google-gemini), [#speech-recognition](https://daily.dev/tags/speech-recognition) [View this post on daily.dev](https://daily.dev/posts/how-to-build-with-gemini-3-5-transcribe-q6cozyqbn) ```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":"How to build with Gemini 3.5 Transcribe","url":"https://daily.dev/posts/how-to-build-with-gemini-3-5-transcribe-q6cozyqbn","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-to-build-with-gemini-3-5-transcribe-q6cozyqbn"},"datePublished":"2026-08-26T21:56:27.207Z","dateModified":"2026-08-26T21:57:31.926Z","description":"Google introduces Gemini 3.5 Transcribe, its first Gemini-based transcription model, available both for batch use on the Interactions API and real-time use on...","image":"https://i.ytimg.com/vi/PWPsZssgfDo/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/PWPsZssgfDo/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Google for Developers","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":"Google for Developers","logo":"https://media.daily.dev/image/upload/s--jj3nxRoG--/f_auto/v1725035497/logos/googledevelopers","url":"https://daily.dev/sources/googledevelopers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-to-build-with-gemini-3-5-transcribe-q6cozyqbn","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"google,llm,google-gemini,speech-recognition","timeRequired":"PT4M","video":{"@type":"VideoObject","name":"How to build with Gemini 3.5 Transcribe","description":"Google introduces Gemini 3.5 Transcribe, its first Gemini-based transcription model, available both for batch use on the Interactions API and real-time use on...","thumbnailUrl":"https://i.ytimg.com/vi/PWPsZssgfDo/sddefault.jpg","uploadDate":"2026-08-26T21:56:27.207Z","duration":"PT4M","url":"https://api.daily.dev/r/Q6COzYQbn","embedUrl":"https://www.youtube.com/embed/PWPsZssgfDo"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Google for Developers","item":"https://daily.dev/sources/googledevelopers"},{"@type":"ListItem","position":3,"name":"How to build with Gemini 3.5 Transcribe"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/how-to-build-with-gemini-3-5-transcribe-q6cozyqbn#faq","mainEntity":[{"@type":"Question","name":"What is Gemini 3.5 Transcribe and how is it different from traditional transcription models?","acceptedAnswer":{"@type":"Answer","text":"Gemini 3.5 Transcribe is Google's first Gemini-based transcription model, available for batch transcription on the Interactions API and real-time transcription on the Live API. Because it is LLM-based rather than a traditional acoustic model, it handles alphanumeric strings, email addresses, and phone numbers more accurately, supports custom vocabulary and language hints, and can self-correct mistakes mid-transcript. Developers evaluating transcription APIs can follow Gemini's evolving capabilities on daily.dev."}},{"@type":"Question","name":"Does Gemini 3.5 Transcribe support languages other than the one specified in language hints?","acceptedAnswer":{"@type":"Answer","text":"Yes, Gemini 3.5 Transcribe can recognize and transcribe over 70 languages automatically even when language hints are set to only English. Setting language hints or codes still improves transcription accuracy, but the model's underlying audio understanding allows it to detect and correctly transcribe mixed-language speech, such as English mixed with German number terms. Teams building multilingual voice apps can track transcription model updates like this on daily.dev."}},{"@type":"Question","name":"Can Gemini 3.5 Transcribe correctly format spoken email addresses and phone numbers?","acceptedAnswer":{"@type":"Answer","text":"Yes, Gemini 3.5 Transcribe can correctly format spoken email addresses, such as converting a spelled-out address into the proper 'name@google.com' format, and it recognizes phone number formats across regions, including US ten-digit numbers and Singapore's eight-digit numbers, correcting itself if an initial guess was wrong. Anyone integrating voice input into forms can watch for accuracy gains like this on daily.dev."}}]} ```