Overview
A new full-duplex real-time voice version in OpenAI’s GPT-Live family, able to listen and respond continuously and handle pauses and interruptions.
GPT-Live-1.1
A new full-duplex real-time voice version in OpenAI’s GPT-Live family, able to listen and respond continuously and handle pauses and interruptions.
OpenAI began rolling GPT-Live-1.1 out in ChatGPT Voice on 2026-10-15; the system card says Plus and higher tiers, including Codex and Dots, default to it. No API model ID is published in these sources.
MODEL NUMBER144
- First public date
- 2026-10-15
- Organization
- OpenAI
- Family
- GPT
01
Specifications
Only published specifications are shown.
02
Overview
Why it mattered
OpenAI’s system card identifies it as the successor to GPT-Live-1; it is recorded as a model version, without treating the ChatGPT Voice rollout as an API release.
PreviousGPT-Live-1— · — ctx
CurrentGPT-Live-1.1— · — ctx
04
Architecture & capabilities
Model capabilities
Native audioReal-time audio
05
Release history
OpenAI is rolling out GPT-Live-1.1 and the lighter Quip in ChatGPT Voice; its system card identifies them as successors to GPT-Live-1 and GPT-Live-1 mini. Both retain full-duplex voice interaction, and these sources publish no API model IDs.
View source06
Related models
Select a card to view the related model.
07
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.