
GPT-Live-1.1 API: Full-duplex voice model for multilingual agents
In brief
GPT-Live-1.1 is a full-duplex voice model in the OpenAI API for multilingual conversations 4. Using model ID gpt-live-1.1 on the v1/live/sessions endpoint, it improves accent consistency, transcription of details like letters and numbers, and plain-language backend delegation 134. A new standby mode pauses inference after 5 to 60 seconds of silence on WebRTC calls 1.
Who can use it
Available in the OpenAI API on the v1/live/sessions endpoint using model ID gpt-live-1.1 41. Active voice sessions cost $0.05 per minute, and WebRTC standby mode costs $0.02 per minute, with backend model and tool usage billed separately 1. The model has also powered voice in ChatGPT Plus and Pro since October 15 1.
Does this affect you?
- DevelopersYou can call gpt-live-1.1 on v1/live/sessions, configure voices and delegation modes, and manage transcripts, audio, and standby timeouts in code 412.
- Product managersYou can define voice assistant personalities, backchannel and interruption policies, and plain-language delegation rules without token-based handoff tags 33.
- FoundersStandby pricing at $0.02 per minute during WebRTC silence and separate concurrent-session limits help you manage voice agent costs and scaling 14.
- Everyday usersThis launch targets API developers, though the same model has already powered voice in ChatGPT Plus and Pro since October 15 1.
Availability
Sources
5 merged into this card- 1GPT-Live-1.1 has arrived in the APIAnnouncement · community.openai.com · 20.11
- 2Managing GPT-Live sessionsHow-to guide · developers.openai.com
- 3Prompting GPT-LiveHow-to guide · developers.openai.com
- 4GPT-Live-1.1 ModelHow-to guide · developers.openai.com
- 5OpenAI API changelog — November 19, 2026Release notes · platform.openai.com · 19.11
More from OpenAI
GPT-6.2 Sol and Astra added to Codex model catalogs
OpenAI added GPT-6.2 Sol and Astra to the model catalogs in Codex 0.171.0, with Sol set as the default selection.
Remote Sessions in codex exec
OpenAI's Codex CLI now allows users to start or resume noninteractive sessions on an existing app server via the new `codex exec --remote <ADDR>` flag.