WebRTC Live.

 UP NEXT! WebRTC Live Episode 114

WebRTC Live #114: An Insider’s Look at OpenAI’s Rearchitected WebRTC Stack

“Real-time voice AI only works when infrastructure makes latency feel invisible. For us, that meant changing the shape of our WebRTC deployment without changing what clients expect from WebRTC itself.”

We’ll get the details behind this WebRTC infrastructure overhaul directly from the source: Yi Zhang, co-author of OpenAI’s deep-dive post, How OpenAI delivers low-latency voice AI at scale. Yi was part of the team that rearchitected OpenAI’s entire WebRTC stack for global scale, addressing pauses, interruptions, and delayed barge-in for ChatGPT voice users, developers building with the Realtime API, and agents operating in interactive voice workflows.

Yi will dive into what it took to make WebRTC work cleanly inside Kubernetes, how separating stateless packet forwarding from stateful session ownership reshaped their infrastructure, the ICE ufrag routing technique that enables deterministic first-packet routing, and what this architecture means for developers building with the OpenAI Realtime API today.

A veteran of Meta and Microsoft with a PhD in Engineering from the University of Wisconsin–Madison, Yi knows this territory from the inside out, and we’re looking forward to hearing his insights firsthand.

Wednesday, June 24 at 12:30 pm Eastern

Register for WebRTC Live 114