# GPT-Live-1 support through LiveKit

**URL:** <https://community.livekit.io/t/gpt-live-1-support-through-livekit/2033>\
**Category:** Announcements\
**Created:** [September 11, 2026, 7:32am UTC](https://community.livekit.io/t/gpt-live-1-support-through-livekit/2033 "2026-09-11T07:32:21Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![darryncampbell](https://sea1.discourse-cdn.com/flex001/user_avatar/community.livekit.io/darryncampbell/32/20_2.png) [@darryncampbell](https://community.livekit.io/u/darryncampbell)\
**Post date:** [September 11, 2026, 7:32am UTC](https://community.livekit.io/t/gpt-live-1-support-through-livekit/2033/1 "2026-09-11T07:32:21Z")

</div>

Most voice agents still take turns: listen, respond, listen again.

Interrupt one mid-sentence and it talks over you or resets. Kick off a slow lookup and you’re sitting in dead air until it’s done.

GPT-Live-1 from OpenAI for Developers doesn’t work that way. It’s full-duplex, listening and speaking at once, so it handles real interruptions and hands reasoning and tool calls off to a backend model instead of freezing the conversation while it works.

We’ve brought it into LiveKit Agents as a new plugin, GPTLiveModel, same AgentSession API you’re already building on.

**Watch the demo:**

[![](https://us1.discourse-cdn.com/flex001/uploads/livekit2/original/2X/e/eed021a6b926ae53433b01813d78544d51d1c00c.jpeg "OpenAI's new voice model doesn't stop talking to think") ](https://www.youtube.com/watch?v=yj-K4kvGgsY)

### Resources

- [Technical documentation](https://docs.livekit.io/agents/models/realtime/plugins/gpt-live/?utm_medium=organicsocial&utm_source=discourse)