OpenAI Launches Full-Duplex Speech Model

智东西 · wechat · 2026-07-09

OpenAI has launched GPT-Live, its first full-duplex real-time speech model capable of listening and speaking simultaneously, available in two versions: GPT-Live-1 and GPT-Live-1mini. It can listen, think, and respond while the user is still talking, supporting interruptions, additions, and follow-up questions for a conversational rhythm that feels much closer to a real human.

The model also decouples real-time conversation from deep reasoning: GPT-Live handles the voice interaction, while complex searches and reasoning are processed in parallel by a backend model, GPT-5.5. Currently, GPT-Live is live on the ChatGPT App and web, with API access rolling out later.

Related event: OpenAI Launches GPT-5.6, ChatGPT Work, and Desktop App Overhaul(136 posts)→

Original post →

More from Models

Models channel →