Build more natural voice experiences with GPT‑Live‑1 in the API

OpenAI is launching GPT-Live-1 in its API, enabling developers to build voice-enabled applications and workflows. This model, first seen in ChatGPT, can listen and speak simultaneously and delegate reasoning to paired models and tools. GPT-Live-1 improves Full Duplex Bench performance by 30 percentage points over GPT-Realtime-2.1 and ranks #1 on Tau3 when paired with GPT-6 Astra. OpenAI Presence also utilizes GPT-Live-1 for real-time voice interactions, helping enterprises deploy AI agents.

This release marks the first time GPT-Live-1 is available via API, unlike its prior exclusive use within ChatGPT, and it shows a 30 percentage point performance gain over GPT-Realtime-2.1.