--- title: How OpenAI delivers low-latency voice AI at scale description: OpenAI rebuilt its WebRTC stack to handle real-time voice AI at scale for over 900 million weekly active users. The core challenge was that the conventional... canonical: https://daily.dev/posts/how-openai-delivers-low-latency-voice-ai-at-scale-k9soex1od twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How OpenAI delivers low-latency voice AI at scale | daily.dev og:description: OpenAI rebuilt its WebRTC stack to handle real-time voice AI at scale for over 900 million weekly active users. The core challenge was that the conventional... og:url: https://daily.dev/posts/how-openai-delivers-low-latency-voice-ai-at-scale-k9soex1od og:image: https://api.daily.dev/og/posts/k9soeX1OD.png og:image:alt: How OpenAI delivers low-latency voice AI at scale 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 OpenAI delivers low-latency voice AI at scale **[Hacker News](https://daily.dev/sources/hn)** · 14 min read · 0 upvotes · 0 comments ## Summary OpenAI rebuilt its WebRTC stack to handle real-time voice AI at scale for over 900 million weekly active users. The core challenge was that the conventional one-port-per-session WebRTC model doesn't fit Kubernetes infrastructure well. Their solution splits packet routing from protocol termination using a relay plus transceiver architecture: a lightweight stateless relay layer handles UDP forwarding with a small public footprint, while stateful transceivers own all WebRTC session state (ICE, DTLS, SRTP). Routing is achieved by encoding destination metadata into the ICE username fragment (ufrag), enabling deterministic first-packet routing without hot-path lookups. The relay is written in Go using SO_REUSEPORT, thread pinning, and pre-allocated buffers for efficiency. A globally distributed relay fleet (Global Relay) reduces first-hop latency by placing ingress close to users worldwide, with Cloudflare geo-steering for signaling. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How OpenAI Delivers Low-Latency Voice AI for 900M Users](https://daily.dev/posts/how-openai-delivers-low-latency-voice-ai-for-900m-users-dyatzvnes) · ByteByteGo · 18 upvotes · 2 comments - [OpenAI Outlines WebRTC Architecture for Low-Latency Voice AI at Scale](https://daily.dev/posts/openai-outlines-webrtc-architecture-for-low-latency-voice-ai-at-scale-6odkdb00l) · InfoQ · 0 upvotes · 0 comments - [OpenAI’s WebRTC Problem](https://daily.dev/posts/openai-s-webrtc-problem-dmrqc4liz) · Hacker News · 0 upvotes · 0 comments - [How WebRTC Scales: Signaling, NAT Traversal, and the Mesh/SFU/MCU Tradeoff](https://daily.dev/posts/how-webrtc-scales-signaling-nat-traversal-and-the-mesh-sfu-mcu-tradeoff-muxbaugy1) · freeCodeCamp · 0 upvotes · 0 comments - [OpenAI Details GPT-Live’s Architecture for Continuous Stateful Voice Interaction](https://daily.dev/posts/openai-details-gpt-live-s-architecture-for-continuous-stateful-voice-interaction-um8nuvvop) · InfoQ · 1 upvotes · 0 comments --- Tags: [#golang](https://daily.dev/tags/golang), [#kubernetes](https://daily.dev/tags/kubernetes), [#networking](https://daily.dev/tags/networking), [#webrtc](https://daily.dev/tags/webrtc) [View this post on daily.dev](https://daily.dev/posts/how-openai-delivers-low-latency-voice-ai-at-scale-k9soex1od) ```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 OpenAI delivers low-latency voice AI at scale","url":"https://daily.dev/posts/how-openai-delivers-low-latency-voice-ai-at-scale-k9soex1od","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-openai-delivers-low-latency-voice-ai-at-scale-k9soex1od"},"datePublished":"2026-05-04T21:21:08.116Z","dateModified":"2026-10-14T02:30:08.805Z","description":"OpenAI rebuilt its WebRTC stack to handle real-time voice AI at scale for over 900 million weekly active users. The core challenge was that the conventional...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/18f43de4431985f5a34b5453b4d7b872?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/18f43de4431985f5a34b5453b4d7b872?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Hacker News","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":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-openai-delivers-low-latency-voice-ai-at-scale-k9soex1od","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"golang,kubernetes,networking,webrtc","timeRequired":"PT14M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"How OpenAI delivers low-latency voice AI at scale"}]} ```