OpenAI launches full-duplex GPT-Live-1 and GPT-Live-1 mini voice models

OpenAI unveiled GPT-Live-1 and GPT-Live-1 mini on July 8, 2026. The real-time voice models can listen and speak simultaneously, so users can interrupt naturally. OpenAI offers the proprietary models through its API for low-latency applications such as live interpreting, customer service and accessibility.

Visit original source