GPT-Live-1 separates speech from café noise and lets you steer mid-sentence

OpenAIDevs · x · 2026-09-11

In a follow-up, OpenAI's developer account detailed GPT-Live-1's conversational fluidity: the model distinguishes speech from background noise so café chatter doesn't stop the conversation, and users can add a detail or change direction mid-conversation without waiting for the model to finish its turn.

Related event: OpenAI launches full-duplex speech model GPT-Live-1 on API(26 posts)→

Original post →

More from Models

Models channel →