@gdb: GPT-Live is a new architecture and stack for realtime audio:
Summary
OpenAI announces GPT-Live, a new architecture and stack for realtime audio that enables listening while speaking, with continuous audio flow for deeper reasoning and tool use without interrupting conversation.
View Cached Full Text
Cached at: 08/04/26, 10:15 PM
GPT-Live is a new architecture and stack for realtime audio:
OpenAI (@OpenAI): GPT-Live can listen while it speaks.
To make that feel natural at ChatGPT scale, we rebuilt the voice stack from client to model.
This new architecture keeps audio flowing continuously, so deeper reasoning and tool use don’t interrupt the conversation.
Similar Articles
@gdb: GPT-Live in the API, for empowering builders to create new kinds of applications:
GPT-Live-1 is now available in the API, enabling developers to create voice-based applications with real-time conversational capabilities similar to ChatGPT.
GPT‑Live
OpenAI announces GPT-Live, a new full-duplex voice model that enables more natural, real-time conversations by allowing simultaneous listening and speaking, with GPT-5.5 as the backend model.
@gdb: GPT-Realtime-2 for instantly translating audio in realtime
GPT-Realtime-2 is introduced as a tool for instant real-time audio translation.
GPT-Live-1 is now in the API
OpenAI has released GPT-Live-1, a full-duplex AI model in the API that enables real-time voice conversations with background noise handling and integration with backend reasoning models.
OPEN AI: How we built a realtime system for responsive voice AI in six months
OpenAI describes how they built GPT-Live, a full-duplex realtime voice AI system that eliminates the turn detector, enabling natural continuous conversation. The article details architecture improvements in inference, context management, and media transport over six months.