--- title: ElevenLabs launches Eleven Realtime, a managed voice... description: ElevenLabs launched Eleven Realtime, a managed voice agent stack with two speech-to-speech models, Mini and Max. Both fold speech recognition, reasoning,... canonical: https://daily.dev/posts/elevenlabs-launches-eleven-realtime-a-managed-voice-agent-stack-with-mini-and-max-models-ejys4kcji twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: ElevenLabs launches Eleven Realtime, a managed voice agent stack with Mini and Max models | daily.dev og:description: ElevenLabs launched Eleven Realtime, a managed voice agent stack with two speech-to-speech models, Mini and Max. Both fold speech recognition, reasoning,... og:url: https://daily.dev/posts/elevenlabs-launches-eleven-realtime-a-managed-voice-agent-stack-with-mini-and-max-models-ejys4kcji og:image: https://api.daily.dev/og/posts/EJYS4KcJI.png og:image:alt: ElevenLabs launches Eleven Realtime, a managed voice agent stack with Mini and Max models 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 launches Eleven Realtime, a managed voice agent stack with Mini and Max models **[Collections](https://daily.dev/sources/collections)** · 3 min read · 1 upvotes · 0 comments ## Summary ElevenLabs launched Eleven Realtime, a managed voice agent stack with two speech-to-speech models, Mini and Max. Both fold speech recognition, reasoning, turn-taking and voice generation into one managed system, but developers can't configure the underlying models independently. On Big Bench Audio, Mini scores 75.9% versus Max's 98.8%, with tool-use task completion at 60.3% and 87.1%. Latency is 620ms for Mini and 570ms for Max. Both support over 90 languages and 17,000+ voices, and the Realtime API speaks OpenAI's Realtime protocol over WebSocket. Mini lacks Zero Retention Mode and HIPAA support; Max offers both in the US and EU but not India or Singapore. ## Content ElevenLabs has released Eleven Realtime, a pair of speech-to-speech models for voice agents: Eleven Realtime v1 Max and Eleven Realtime v1 Mini. Instead of making developers wire together speech recognition, an LLM, turn-taking and text-to-speech, the company bundles all of it into one managed system. ## Max and Mini Mini is tuned for natural conversation at low cost. According to ElevenLabs, it knows when you've finished talking, recovers if you interrupt, and doesn't stop mid-sentence because you said "mm-hmm." Max is aimed at heavier work like customer support and lead qualification. ElevenLabs says it handles multi-step requests, calls tools to look things up, and takes action. The reported numbers: | | Max | Mini | |---|---|---| | Big Bench Audio | 98.8% | 75.9% | | Tool-use tasks completed | 87.1% | 60.3% | | Time to first speech | ~570ms (0.57s) | ~620ms | The latency gap is small, so the real difference is accuracy and tool use. ElevenLabs also claims no model on the Artificial Analysis leaderboard is both faster and more accurate than Max. That's the company's claim, and it hasn't been tested at scale by outside developers yet. Both models support more than 90 languages and can use any of the 17,000+ voices in ElevenLabs' library. ## Where it runs The models are live on the ElevenAgents platform, which can deploy to phone lines, websites, WhatsApp and contact center platforms. They're also available through the Realtime API. That API speaks OpenAI's Realtime protocol over WebSocket, and ElevenLabs describes it as OpenAI compatible, so migrating can mean swapping the endpoint. One catch: an app built on WebRTC has to switch transports and handle audio capture itself. ## What developers give up The tradeoff is control. Developers can't pick or independently configure the underlying models, so you get a managed stack or nothing. There are compliance gaps too. Mini has no Zero Retention Mode and no HIPAA support. Max offers both in the US and EU, but not in India or Singapore. ## My take I think the interesting part is timing, not sound quality. Knowing when to jump in, when to stay quiet, when to correct course mid-sentence is what makes a voice interaction feel human. Plenty of voices already sound fine. If these numbers hold up in production, the differentiator between voice products will be how well they listen. Whether teams will accept a black-box pipeline to get there is the open question. ## Questions this post answers ### What is the latency difference between ElevenLabs Realtime Mini and Max models? Max is actually faster than Mini despite being the more capable model: Max runs at 570ms latency versus Mini's 620ms. Max also scores much higher on accuracy, 98.8% versus 75.9% on Big Bench Audio, and 87.1% versus 60.3% on tool-use task completion, making the latency trade-off negligible for choosing Max. _Developers picking a voice agent model can compare these exact benchmark numbers on daily.dev._ ### Does ElevenLabs Realtime support HIPAA compliance? Only the Max model supports HIPAA and Zero Retention Mode, and only in the US and EU, not in India or Singapore. The Mini model has no Zero Retention Mode and no HIPAA support at all, so teams in regulated industries need to check region and model availability before committing. _Teams scoping compliant voice agent deployments can track these regional limits on daily.dev._ ### Is ElevenLabs Realtime API compatible with OpenAI's Realtime API? ElevenLabs describes its Realtime API as OpenAI compatible, speaking OpenAI's Realtime protocol over WebSocket. However, migration is not always a simple endpoint swap: an app built on WebRTC transport has to switch transports and handle audio capture itself when moving to this API. _Developers weighing a migration between voice APIs can follow compatibility caveats like this on daily.dev._ ## Community take How the wider developer community reacted, aggregated from 1 discussion and 25 comments across x (as of 2026-10-21). **TL;DR:** Reactions focus heavily on the sub-second latency (~0.57s) as a milestone for voice agents feeling conversational, while many ask practical follow-up questions about pricing, interruption handling, and real-world (non-benchmark) performance. **Sentiment:** 45% positive · 50% mixed · 5% skeptical **The case for** - Sub-second time-to-first-speech is seen as crossing the threshold where voice agents feel like real conversation rather than a phone menu. - The Mini/Max split makes sense to some, letting easy turns route to a cheaper model and hard ones to the stronger one. - High Big Bench Audio score (98.8%) is viewed as a notable jump in quality. **The pushback** - Several ask whether the latency number is measured from end-of-speech or from the API request, suspecting a gap that matters for real phone calls. - Handling of interruptions, barge-in, and mid-sentence cutoffs is repeatedly flagged as the real test, not benchmark scores. - Pricing for Mini's 'low cost' claim is questioned as vague without concrete per-minute or per-turn numbers. - Performance on non-English or accented speech is questioned as an unproven area despite the latency claims. **By community** - x (mixed): Excitement about the sub-second latency is paired with many practical questions about interruption handling, pricing, and real-call performance rather than benchmark numbers. **Open questions** - Is the 0.57s latency measured from when the user stops speaking or from when the request hits the API? - What is the actual per-minute or per-turn pricing for Mini? - How well does the model handle interruptions, mumbling, and mid-sentence changes of mind in real calls? - How does performance hold up on non-English languages like Hebrew or Korean? - Is Mini's time-to-first-speech close to Max's 0.57s? **Highlights** > @testingcatalog is the 0.57s counted from when the user stops talking or from when the request hits their API? big gap between those for a phone agent > — [Chahatusharma on x](https://x.com/Chahatusharma/status/2112780330725970029) > @testingcatalog Mini is the interesting one here. Low cost and natural conversation is what gets voice agents used daily. Max at 98.8% on Big Bench Audio and 0.57s to reply looks great, but the real test is a caller who interrupts, mumbles and changes their mind mid sentence. > — [AaravAITips on x](https://x.com/AaravAITips/status/2112793069703893461) > @testingcatalog 0.57s to first audio is the number that matters for voice agents. Curious how it holds up on non-English speech, Hebrew especially, where latency usually isn't the only thing that degrades. > — [maitz\_team on x](https://x.com/maitz_team/status/2112806152757018759) > @testingcatalog "low cost" for mini needs a number. per-minute pricing? per-turn? the model that wins daily use isn't the best quality — it's the one where the bill is predictable. > — [qaqashish on x](https://x.com/qaqashish/status/2112782406524797005) > @testingcatalog For Eleven Realtime, I care as much about when it stops talking as when it starts. My voice-agent rule: yield when interrupted. A fast talker still needs brakes. > — [wdrozai on x](https://x.com/wdrozai/status/2112793019850334552) **Source threads** - [x](https://x.com/testingcatalog/status/2112778083816140857) · 1 points · 25 comments ## 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 - [MiniMax M2.1: Significantly Enhanced Multi-Language Programming, Built for Real-World Complex Tasks](https://daily.dev/posts/minimax-m2-1-significantly-enhanced-multi-language-programming-built-for-real-world-complex-tasks-zx03qgysi) · Hacker News · 1 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-launches-eleven-realtime-a-managed-voice-agent-stack-with-mini-and-max-models-ejys4kcji) ```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 launches Eleven Realtime, a managed voice agent stack with Mini and Max models","url":"https://daily.dev/posts/elevenlabs-launches-eleven-realtime-a-managed-voice-agent-stack-with-mini-and-max-models-ejys4kcji","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/elevenlabs-launches-eleven-realtime-a-managed-voice-agent-stack-with-mini-and-max-models-ejys4kcji"},"datePublished":"2026-10-20T19:13:13.413Z","dateModified":"2026-10-21T08:29:54.278Z","description":"ElevenLabs launched Eleven Realtime, a managed voice agent stack with two speech-to-speech models, Mini and Max. Both fold speech recognition, reasoning,...","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":"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/elevenlabs-launches-eleven-realtime-a-managed-voice-agent-stack-with-mini-and-max-models-ejys4kcji","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,voice-ai,elevenlabs","timeRequired":"PT3M"} {"@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":"ElevenLabs launches Eleven Realtime, a managed voice agent stack with Mini and Max models"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/elevenlabs-launches-eleven-realtime-a-managed-voice-agent-stack-with-mini-and-max-models-ejys4kcji#faq","mainEntity":[{"@type":"Question","name":"What is the latency difference between ElevenLabs Realtime Mini and Max models?","acceptedAnswer":{"@type":"Answer","text":"Max is actually faster than Mini despite being the more capable model: Max runs at 570ms latency versus Mini's 620ms. Max also scores much higher on accuracy, 98.8% versus 75.9% on Big Bench Audio, and 87.1% versus 60.3% on tool-use task completion, making the latency trade-off negligible for choosing Max. Developers picking a voice agent model can compare these exact benchmark numbers on daily.dev."}},{"@type":"Question","name":"Does ElevenLabs Realtime support HIPAA compliance?","acceptedAnswer":{"@type":"Answer","text":"Only the Max model supports HIPAA and Zero Retention Mode, and only in the US and EU, not in India or Singapore. The Mini model has no Zero Retention Mode and no HIPAA support at all, so teams in regulated industries need to check region and model availability before committing. Teams scoping compliant voice agent deployments can track these regional limits on daily.dev."}},{"@type":"Question","name":"Is ElevenLabs Realtime API compatible with OpenAI's Realtime API?","acceptedAnswer":{"@type":"Answer","text":"ElevenLabs describes its Realtime API as OpenAI compatible, speaking OpenAI's Realtime protocol over WebSocket. However, migration is not always a simple endpoint swap: an app built on WebRTC transport has to switch transports and handle audio capture itself when moving to this API. Developers weighing a migration between voice APIs can follow compatibility caveats like this on daily.dev."}}]} ```