Add voice to your agent

An experimental voice pipeline for the Agents SDK enables real-time voice interactions over WebSockets. Developers can now build agents with continuous STT and TTS in just ~30 lines of server-side code.

Why it matters: Useful because it points to a real product or platform update, not just general hype.

Useful for: Most useful for builders, product teams, UX people, and anyone tracking practical web and AI shifts.

Different because: Worth opening when the release changes what teams can actually ship, integrate, or test soon.