--- title: Your Voice Agent Doesn't Need a Frontier Model - Joel... description: Building real-time voice AI agents requires sub-second response times, making large frontier models impractical. The Ace voice tutor team at Microsoft offloads... canonical: https://daily.dev/posts/your-voice-agent-doesn-t-need-a-frontier-model---joel-allou-ornella-bahidika-microsoft-8ycx2x1yb twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Your Voice Agent Doesn't Need a Frontier Model - Joel Allou & Ornella Bahidika, Microsoft | daily.dev og:description: Building real-time voice AI agents requires sub-second response times, making large frontier models impractical. The Ace voice tutor team at Microsoft offloads... og:url: https://daily.dev/posts/your-voice-agent-doesn-t-need-a-frontier-model---joel-allou-ornella-bahidika-microsoft-8ycx2x1yb og:image: https://api.daily.dev/og/posts/8YCX2X1yB.png og:image:alt: Your Voice Agent Doesn't Need a Frontier Model - Joel Allou & Ornella Bahidika, Microsoft 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. # Your Voice Agent Doesn't Need a Frontier Model - Joel Allou & Ornella Bahidika, Microsoft **[AI Engineer](https://daily.dev/sources/aidotengineer)** · 5 min read · 0 upvotes · 0 comments ## Summary Building real-time voice AI agents requires sub-second response times, making large frontier models impractical. The Ace voice tutor team at Microsoft offloads all reasoning, lesson logic, and state tracking to a state machine and scaffolding code, leaving the language model responsible only for generating speech. This approach uses a smaller, faster model (Claude Haiku 4.5) to achieve ~900ms response times versus several seconds with a frontier model like Claude Opus 4.7. The tradeoff is upfront engineering cost to build the scaffolding, but that cost is paid once in code rather than on every inference call. The core principle: pick the fastest model your latency budget allows, then invest the rest of your effort in scaffolding. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How to Choose Between Small and Frontier Models](https://daily.dev/posts/how-to-choose-between-small-and-frontier-models-fwsu2bqxo) · Towards Data Science · 0 upvotes · 0 comments - [A Hybrid Approach to Agentic Development with Local Models](https://daily.dev/posts/a-hybrid-approach-to-agentic-development-with-local-models-gb8uzijo0) · Atomic Spin · 2 upvotes · 1 comments - [AI Voice Agents in Production \(2026 Developer Guide\)](https://daily.dev/posts/ai-voice-agents-in-production-2026-developer-guide--xxj1vmli1) · Alex CloudStar · 0 upvotes · 0 comments - [Do you really need the latest AI model? Or are you just upgrading your tech ego?](https://daily.dev/posts/do-you-really-need-the-latest-ai-model-or-are-you-just-upgrading-your-tech-ego--o2wyzwvun) · Codemotion · 0 upvotes · 0 comments --- Tags: [#general-programming](https://daily.dev/tags/general-programming), [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#voice-ai](https://daily.dev/tags/voice-ai) [View this post on daily.dev](https://daily.dev/posts/your-voice-agent-doesn-t-need-a-frontier-model---joel-allou-ornella-bahidika-microsoft-8ycx2x1yb) ```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":"Your Voice Agent Doesn't Need a Frontier Model - Joel Allou & Ornella Bahidika, Microsoft","url":"https://daily.dev/posts/your-voice-agent-doesn-t-need-a-frontier-model---joel-allou-ornella-bahidika-microsoft-8ycx2x1yb","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/your-voice-agent-doesn-t-need-a-frontier-model---joel-allou-ornella-bahidika-microsoft-8ycx2x1yb"},"datePublished":"2026-07-20T06:39:37.423Z","dateModified":"2026-07-20T21:27:36.346Z","description":"Building real-time voice AI agents requires sub-second response times, making large frontier models impractical. The Ace voice tutor team at Microsoft offloads...","image":"https://i.ytimg.com/vi/fnLBmfsI_Fg/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/fnLBmfsI_Fg/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AI Engineer","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":"AI Engineer","logo":"https://media.daily.dev/image/upload/s--u5PucxNT--/f_auto/v1724338940/logos/aidotengineer","url":"https://daily.dev/sources/aidotengineer"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/your-voice-agent-doesn-t-need-a-frontier-model---joel-allou-ornella-bahidika-microsoft-8ycx2x1yb","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"general-programming,llm,ai-agents,voice-ai","timeRequired":"PT5M","video":{"@type":"VideoObject","name":"Your Voice Agent Doesn't Need a Frontier Model - Joel Allou & Ornella Bahidika, Microsoft","description":"Building real-time voice AI agents requires sub-second response times, making large frontier models impractical. The Ace voice tutor team at Microsoft offloads...","thumbnailUrl":"https://i.ytimg.com/vi/fnLBmfsI_Fg/sddefault.jpg","uploadDate":"2026-07-20T06:39:37.423Z","duration":"PT5M","url":"https://api.daily.dev/r/8YCX2X1yB","embedUrl":"https://www.youtube.com/embed/fnLBmfsI_Fg"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AI Engineer","item":"https://daily.dev/sources/aidotengineer"},{"@type":"ListItem","position":3,"name":"Your Voice Agent Doesn't Need a Frontier Model - Joel Allou & Ornella Bahidika, Microsoft"}]} ```