--- title: AI Gateway now supports streaming transcription | daily.dev description: Vercel's AI Gateway now supports streaming transcription in beta, allowing developers to stream live audio and receive transcript updates in real time as the... canonical: https://daily.dev/posts/ai-gateway-now-supports-streaming-transcription-xgbwbzesl twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: AI Gateway now supports streaming transcription | daily.dev og:description: Vercel's AI Gateway now supports streaming transcription in beta, allowing developers to stream live audio and receive transcript updates in real time as the... og:url: https://daily.dev/posts/ai-gateway-now-supports-streaming-transcription-xgbwbzesl og:image: https://api.daily.dev/og/posts/XGbWBZEsl.png og:image:alt: AI Gateway now supports streaming transcription 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. # AI Gateway now supports streaming transcription **[Vercel](https://daily.dev/sources/vercel)** · 2 min read · 0 upvotes · 0 comments ## Summary Vercel's AI Gateway now supports streaming transcription in beta, allowing developers to stream live audio and receive transcript updates in real time as the model produces them. Previously, transcription required a complete audio file and returned a single response. The feature is accessible via the AI SDK's `streamTranscribe` function and works with any streaming-capable transcription model, including `openai/gpt-realtime-whisper` and `xai/grok-stt`. It enables low-latency use cases like live captioning, voice input, and adding voice mode to text-based agents. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I stream live audio transcription using the AI SDK's streamTranscribe function? Use the experimental_streamTranscribe function from the ai package, passing a model like openai/gpt-realtime-whisper, a ReadableStream of audio, and an inputAudioFormat config (e.g., audio/pcm at 24000 rate). Iterate over result.fullStream and check for parts with type 'transcript-delta' to print each piece of transcript as it arrives, rather than waiting for a full response. _daily.dev surfaces AI SDK updates like this for developers wiring up real-time voice features._ ### Does Vercel AI Gateway support streaming transcription instead of only full-file transcription? Yes, streaming transcription is now supported in beta, replacing the previous requirement of submitting a complete audio file and waiting for a single full-transcript response. Audio can now be streamed in as it's captured, with transcript updates returned incrementally, reducing latency for use cases such as live captioning and voice input. _Track gateway changes like this on daily.dev when your voice pipeline depends on low transcription latency._ ### Which transcription models work with streaming transcription on Vercel AI Gateway? Any streaming-capable transcription model works, including openai/gpt-realtime-whisper and xai/grok-stt, since the same streamTranscribe code works across providers by simply swapping the model string. This lets developers switch providers without rewriting their transcription integration. _daily.dev helps developers comparing transcription model providers keep up with what's newly supported._ ## Similar posts on daily.dev - [OpenAI launches new voice intelligence features in its API](https://daily.dev/posts/openai-launches-new-voice-intelligence-features-in-its-api-ymtm53lpv) · TechCrunch · 0 upvotes · 0 comments --- Tags: [#vercel](https://daily.dev/tags/vercel), [#speech-recognition](https://daily.dev/tags/speech-recognition), [#ai-sdk](https://daily.dev/tags/ai-sdk) [View this post on daily.dev](https://daily.dev/posts/ai-gateway-now-supports-streaming-transcription-xgbwbzesl) ```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":"AI Gateway now supports streaming transcription","url":"https://daily.dev/posts/ai-gateway-now-supports-streaming-transcription-xgbwbzesl","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/ai-gateway-now-supports-streaming-transcription-xgbwbzesl"},"datePublished":"2026-07-22T17:57:45.415Z","dateModified":"2026-09-13T18:28:29.061Z","description":"Vercel's AI Gateway now supports streaming transcription in beta, allowing developers to stream live audio and receive transcript updates in real time as the...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/006a46cf00036fe5f56275a8ce13adb2?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/006a46cf00036fe5f56275a8ce13adb2?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Vercel","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":"Vercel","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/04cca7235cf84db092f24b7ba427b3e1","url":"https://daily.dev/sources/vercel"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/ai-gateway-now-supports-streaming-transcription-xgbwbzesl","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"vercel,speech-recognition,ai-sdk","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Vercel","item":"https://daily.dev/sources/vercel"},{"@type":"ListItem","position":3,"name":"AI Gateway now supports streaming transcription"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/ai-gateway-now-supports-streaming-transcription-xgbwbzesl#faq","mainEntity":[{"@type":"Question","name":"How do I stream live audio transcription using the AI SDK's streamTranscribe function?","acceptedAnswer":{"@type":"Answer","text":"Use the experimental_streamTranscribe function from the ai package, passing a model like openai/gpt-realtime-whisper, a ReadableStream of audio, and an inputAudioFormat config (e.g., audio/pcm at 24000 rate). Iterate over result.fullStream and check for parts with type 'transcript-delta' to print each piece of transcript as it arrives, rather than waiting for a full response. daily.dev surfaces AI SDK updates like this for developers wiring up real-time voice features."}},{"@type":"Question","name":"Does Vercel AI Gateway support streaming transcription instead of only full-file transcription?","acceptedAnswer":{"@type":"Answer","text":"Yes, streaming transcription is now supported in beta, replacing the previous requirement of submitting a complete audio file and waiting for a single full-transcript response. Audio can now be streamed in as it's captured, with transcript updates returned incrementally, reducing latency for use cases such as live captioning and voice input. Track gateway changes like this on daily.dev when your voice pipeline depends on low transcription latency."}},{"@type":"Question","name":"Which transcription models work with streaming transcription on Vercel AI Gateway?","acceptedAnswer":{"@type":"Answer","text":"Any streaming-capable transcription model works, including openai/gpt-realtime-whisper and xai/grok-stt, since the same streamTranscribe code works across providers by simply swapping the model string. This lets developers switch providers without rewriting their transcription integration. daily.dev helps developers comparing transcription model providers keep up with what's newly supported."}}]} ```