OpenAI details GPT-Live: a full-duplex voice system that drops the turn detector and streams audio continuously

How we built a realtime system for responsive voice AI in six months

OpenAI published an engineering post on Aug 3 explaining GPT-Live’s realtime voice stack. The key change: they removed the turn detector from the audio path and switched to a full-duplex model that listens and speaks simultaneously. This avoids the old problem of a tiny model guessing when the user has finished, and lets the large model stream audio directly for more natural timing. When deeper reasoning or tool use is needed, the system delegates asynchronously to frontier models like GPT-5.5 without blocking the live voice loop. The team spent six months reworking inference, context management, and media transport to keep latency low end-to-end. The post says this architecture already powers computer control and agent coordination in the ChatGPT desktop app, but it does not disclose specific latency figures or deployment scale.

Why it matters: Official OpenAI engineering post explaining the architecture shift from turn-based to full-duplex voice for GPT-Live, with concrete technical decisions. Not a product launch—it's a developer-facing deep-dive. Hits all three HKR axes. Score stays at 78 rather than 85+ because t...