OpenAI drops turn‑detectors for GPT‑Live’s full‑duplex voice, delivering real‑time chat
OpenAI rewrote its voice stack so the model can listen and speak at the same time, eliminating the lag‑prone turn‑detector that previous systems used. The new architecture streams audio into the model while handling tool use and deeper reasoning on a separate asynchronous path, keeping speech fluid and still tapping GPT‑4‑Turbo‑like intelligence.