GPT-Live-1.1

OpenAI released GPT-Live-1.1 on November 19, 2026, a full-duplex voice model for multilingual conversations in the Live API.

Lab
OpenAI
Release date
Status
Generally available
API model ID
gpt-live-1.1

The OpenAI API changelog entry of November 19, 2026, says gpt-live-1.1 improves pronunciation, accent consistency and transcription in multilingual voice conversations, and can be used in an existing Live session configuration (v1/live/sessions). The model page lists audio and text input and output, and notes that GPT-Live-1.1 and GPT-Live 1 have separate concurrent-session limits.

Modalities
Audio and text input; audio and text output (full-duplex voice)
Availability
OpenAI API (v1/live/sessions).
Official source
developers.openai.com
Last checked

Questions

When was GPT-Live-1.1 released?
November 19, 2026.
What is the model ID?
gpt-live-1.1.
What changed from GPT-Live 1?
OpenAI cites better pronunciation, accent consistency and transcription in multilingual conversations.

Source

Release dates, model IDs and limits come from each lab’s own announcement, changelog, documentation or deprecations page, linked on every model with the date it was last checked. How we pick and check sources: editorial standards.

The Model Press

What are you looking for?

Search by headline, topic or keyword.