https://www.infoq.com InfoQ Realtime API News feed https://www.infoq.com/news/2026/05/openai-voice-ai-scale/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Realtime+API-news <img src="https://res.infoq.com/news/2026/05/openai-voice-ai-scale/en/headerimage/OpenAI-voice-header-1779194151282.jpeg"/><p>OpenAI recently outlined how it adapted WebRTC for low-latency voice AI at global scale. The new architecture replaced a conventional media termination model with a relay-transceiver design better suited to Kubernetes and cloud load balancers. It keeps WebRTC session state in a dedicated transceiver layer while using relays to reduce public UDP exposure and keep media routing close to users.</p> <i>By Eran Stiller</i> Cloud Architecture WebRTC Realtime API Voice-enabled UI OpenAI DevOps Architecture & Design news Wed, 20 May 2026 12:30:00 GMT https://www.infoq.com/news/2026/05/openai-voice-ai-scale/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Realtime+API-news Eran Stiller 2026-05-20T12:30:00Z /news/2026/05/openai-voice-ai-scale/en