--- title: ElevenLabs wants to run your voice agent. Here’s what... description: ElevenLabs launched Eleven Realtime on Tuesday, bundling speech recognition, reasoning, turn-taking, and voice generation into two managed models, Mini and... canonical: https://daily.dev/posts/elevenlabs-wants-to-run-your-voice-agent-here-s-what-developers-give-up--xn78gt6nc twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: ElevenLabs wants to run your voice agent. Here’s what developers give up. | daily.dev og:description: ElevenLabs launched Eleven Realtime on Tuesday, bundling speech recognition, reasoning, turn-taking, and voice generation into two managed models, Mini and... og:url: https://daily.dev/posts/elevenlabs-wants-to-run-your-voice-agent-here-s-what-developers-give-up--xn78gt6nc og:image: https://api.daily.dev/og/posts/Xn78gt6nc.png og:image:alt: ElevenLabs wants to run your voice agent. Here’s what developers give up. 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. # ElevenLabs wants to run your voice agent. Here’s what developers give up. **[The New Stack](https://daily.dev/sources/newstack)** · 4 min read · 0 upvotes · 0 comments ## Summary ElevenLabs launched Eleven Realtime on Tuesday, bundling speech recognition, reasoning, turn-taking, and voice generation into two managed models, Mini and Max. Developers can't select or independently configure the underlying models, trading flexibility for a managed stack. On Big Bench Audio, Max scored 98.8% versus Mini's 75.9%, and Max completed 87.1% of tool-use tasks against Mini's 60.3%. Latency is close: 570ms for Max versus 620ms for Mini. The Realtime API speaks OpenAI's Realtime protocol over WebSocket, but a WebRTC app must switch transports and handle audio capture itself. Mini lacks Zero Retention Mode and HIPAA support, which Max offers in the US and EU but not in India or Singapore. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What's the difference between ElevenLabs Eleven Realtime Mini and Max models? Max scores higher on reasoning and tool use but costs more per token. On Big Bench Audio, Max scored 98.8% versus Mini's 75.9%, and completed 87.1% of tool-use tasks versus Mini's 60.3%. Mini is set as the default and slightly outperforms Max on turn-taking (95.8% vs 94.1% on Full-Duplex-Bench). Mini also lacks Zero Retention Mode and HIPAA support, which Max offers in the US and EU. _daily.dev surfaces comparisons like this for developers picking between voice-agent models._ ### Can I migrate an app from OpenAI's Realtime API to ElevenLabs Eleven Realtime without changing my SDK? Yes, Eleven Realtime speaks the same protocol over the same WebSocket transport as OpenAI's Realtime API, so you only need to change the endpoint and model name. However, the endpoint supports WebSocket only, so a WebRTC-based app must switch transports and handle 24kHz PCM16 audio capture and playback manually, since the SDK only manages that automatically over WebRTC. _developers planning a realtime-API migration track breaking changes like these on daily.dev._ ### Can ElevenLabs Realtime voice agents transfer calls to custom voice-agent pipelines? No. Mini and Max agents can transfer calls between each other, but neither can transfer calls to or from agents running in Custom mode, where developers select and configure the underlying language and speech models themselves. This limits interoperability between ElevenLabs' managed Realtime models and self-configured pipelines. _teams weighing managed versus custom voice-agent architectures follow tradeoffs like this on daily.dev._ ## Similar posts on daily.dev - [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 - [GPT-5.4 Mini for Voice AI: The Low-Latency Solution Developers Need](https://daily.dev/posts/gpt-5-4-mini-for-voice-ai-the-low-latency-solution-developers-need-ju2en4scd) · SitePoint · 1 upvotes · 0 comments - [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: [#ai-agents](https://daily.dev/tags/ai-agents), [#voice-ai](https://daily.dev/tags/voice-ai), [#elevenlabs](https://daily.dev/tags/elevenlabs) [View this post on daily.dev](https://daily.dev/posts/elevenlabs-wants-to-run-your-voice-agent-here-s-what-developers-give-up--xn78gt6nc) ```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":"ElevenLabs wants to run your voice agent. Here’s what developers give up.","url":"https://daily.dev/posts/elevenlabs-wants-to-run-your-voice-agent-here-s-what-developers-give-up--xn78gt6nc","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/elevenlabs-wants-to-run-your-voice-agent-here-s-what-developers-give-up--xn78gt6nc"},"datePublished":"2026-10-20T18:46:56.933Z","dateModified":"2026-10-21T05:29:29.044Z","description":"ElevenLabs launched Eleven Realtime on Tuesday, bundling speech recognition, reasoning, turn-taking, and voice generation into two managed models, Mini and...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b4c006e874130f72701082f2e392887f?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b4c006e874130f72701082f2e392887f?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","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":"The New Stack","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/newstack","url":"https://daily.dev/sources/newstack"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/elevenlabs-wants-to-run-your-voice-agent-here-s-what-developers-give-up--xn78gt6nc","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,voice-ai,elevenlabs","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"ElevenLabs wants to run your voice agent. Here’s what developers give up."}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/elevenlabs-wants-to-run-your-voice-agent-here-s-what-developers-give-up--xn78gt6nc#faq","mainEntity":[{"@type":"Question","name":"What's the difference between ElevenLabs Eleven Realtime Mini and Max models?","acceptedAnswer":{"@type":"Answer","text":"Max scores higher on reasoning and tool use but costs more per token. On Big Bench Audio, Max scored 98.8% versus Mini's 75.9%, and completed 87.1% of tool-use tasks versus Mini's 60.3%. Mini is set as the default and slightly outperforms Max on turn-taking (95.8% vs 94.1% on Full-Duplex-Bench). Mini also lacks Zero Retention Mode and HIPAA support, which Max offers in the US and EU. daily.dev surfaces comparisons like this for developers picking between voice-agent models."}},{"@type":"Question","name":"Can I migrate an app from OpenAI's Realtime API to ElevenLabs Eleven Realtime without changing my SDK?","acceptedAnswer":{"@type":"Answer","text":"Yes, Eleven Realtime speaks the same protocol over the same WebSocket transport as OpenAI's Realtime API, so you only need to change the endpoint and model name. However, the endpoint supports WebSocket only, so a WebRTC-based app must switch transports and handle 24kHz PCM16 audio capture and playback manually, since the SDK only manages that automatically over WebRTC. developers planning a realtime-API migration track breaking changes like these on daily.dev."}},{"@type":"Question","name":"Can ElevenLabs Realtime voice agents transfer calls to custom voice-agent pipelines?","acceptedAnswer":{"@type":"Answer","text":"No. Mini and Max agents can transfer calls between each other, but neither can transfer calls to or from agents running in Custom mode, where developers select and configure the underlying language and speech models themselves. This limits interoperability between ElevenLabs' managed Realtime models and self-configured pipelines. teams weighing managed versus custom voice-agent architectures follow tradeoffs like this on daily.dev."}}]} ```