GPT-Realtime-2
OpenAI's live voice models that can talk, translate speech and write down what is said, made for developers building voice apps.
This came out before trckr began following OpenAI API, so it was added on Nov 8 without an alert. Its release date comes from OpenAI API changelog.
Key facts
- Released
- May 7, 2026
- What it does
- Makes sound: Creates speech, music or other audio.
Can I use it?
In an app
No app mentioned so far.
For developers
Developers can use it now through an API: How developers plug a model into their own apps and pay per use. A model that's "in the API" can be used by programmers, even if it isn't in a chat app yet..
Download
Not downloadable: it runs on the maker's own servers.
Compare GPT-Realtime-2 with
It came out 73 days after GPT-Realtime-1.5, the lab's previous model.
The details
OpenAI released GPT-Realtime-2 with companion realtime translation and Speech-to-text: Turns spoken audio into written text. Also called transcription or ASR. models for live voice apps in the API: How developers plug a model into their own apps and pay per use. A model that's "in the API" can be used by programmers, even if it isn't in a chat app yet..
Model ID: The exact name developers type to use a model, like gpt-5-mini. New IDs often show up in a lab's systems before the official announcement, which is how trckr spots many releases early.
gpt-realtime-2gpt-realtime-translategpt-realtime-whisperTimeline
/OpenAI APIOfficialFirst signal
gpt-realtime-2
/OpenAI APIOfficial
gpt-realtime-translate
/OpenAI APIOfficial
gpt-realtime-whisper
Get alerts like this the moment they happen.
From OpenAI and every other major lab.