Text-to-Speech
GPT Realtime 2 is our most capable realtime voice model. It supports speech-to-speech interactions with configurable reasoning effort, stronger instruction following, and more reliable tool use for complex voice-agent workflows.
1,069
May 2026
realtime
$4/1M
Catalog
Category rows come directly from Artificial Analysis when the endpoint exposes category-level Elo scores.
This Artificial Analysis endpoint does not expose category rows for this model yet.