How OpenAI delivers low-latency voice AI at scale

kept by eddie may 09

OpenAI rearchitected its WebRTC stack into a split relay-plus-transceiver architecture to reduce latency for voice AI at global scale.

Realtime Prompting Guide
OpenAI released gpt-realtime, a speech-to-speech model in the API, and published a prompting guide detailing techniques for instruction following, voice quality, and tool calling.
also on Realtime API, OpenAI, #ai, #developer-tools
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.
also on WebRTC, #cloud-computing, OpenAI, #ai
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.
also on WebRTC, OpenAI, #ai