Home / Models / GPT-Realtime-2.1

GPT-Realtime-2.1

Maker: OpenAI · speech synthesis

A speech-to-speech voice model with configurable reasoning effort and tool use. Takes text, audio and images; runs over the Realtime API (WebRTC, WebSocket, SIP).

Understands

text, audio, images

Produces

text, speech

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.