Reading up on Pion
2 deep · digging since may 05
- How OpenAI Delivers Low-Latency Voice AI for 900M Users
OpenAI splits WebRTC into a stateless relay and a stateful transceiver, using the ICE ufrag for routing to serve 900M voice AI users with low latency.
- How OpenAI delivers low-latency voice AI at scale
OpenAI rebuilt its WebRTC stack with a relay-transceiver architecture to reduce latency and manage scale for real-time voice AI across 900 million users.