GPT-Realtime-2 arrives in the OpenAI API
- Source
- x.com
- Date
people are really starting to use voice to interact with AI, especially when they have a lot of context to dump. GPT-Realtime-2 comes to the API today; it is a pretty big step forward. (we are working on improvements to voice in chat.)
as a side note, young people seem to prefer to interact with AI via voice, and old people, and people in the middle like to type. i wonder if this will change.
Context
GPT-Realtime-2 gives developers control over how much reasoning a voice uses before responding. In its May 7, 2026 announcement, OpenAI describes adjustable reasoning levels that balance response speed against more deliberate handling of complex requests.
The model can also call multiple tools at once and speak brief progress updates while working. That gives a voice application a way to acknowledge a request and explain an ongoing lookup, rather than leaving the caller waiting without feedback. These are capabilities of the developer API; the post separately described ChatGPT voice improvements as work still underway.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Checking sign-in…
Loading comments…