What changed in Realtime 2

Prompt Realtime 2 as a reasoning voice agent, not as a basic voice bot.

Change	What it means for prompts
Reasoning	Allow the model to reason internally for complex tasks before speaking or calling tools. Use preambles to avoid awkward silence or unnecessary filler.
Prompt precision matters more	Replace broad guidance like "be helpful" with clear trigger, action, and exception rules: when to act, what to do, and when not to do it.
Instruction conflicts are more costly	Remove overlapping always, never, only, and must rules unless they are truly required. Define priority when rules compete.
Tool behavior is more steerable	Specify when the assistant should act immediately, ask for missing information, confirm high-precision details, retry after failure, or escalate.
Preambles are first-class behavior	The model may speak brief updates before longer reasoning or tool-use flows. Steer when preambles should appear, how short they should be, and when to skip them.
Expanded context window	gpt-realtime-2 expands the realtime context window from 32k to 128k tokens, making it better suited for long sessions and larger system prompts.

Preambles aren't hidden chain-of-thought. They're short spoken updates such as "I'll check that order now." Don't ask the model to reveal private reasoning.