Release2026-10-27

DeepMind announced Genie 4, a new world model for real-time interactive simulation. It generates native audio, ambient sounds, and interactive dialogue alongside the world. Genie 4 simulates advanced physics, natural human motion, and complex events. Users can steer scenes in real-time with text prompts. It builds on Gemini models for reasoning and coherence. Genie 4 is rolling out as a research preview to trusted testers. Early access is limited to Google AI Ultra subscribers, Gemini API partners, and Google AI Studio users. A waitlist is open for Project Genie access.

What changed

Genie 3 offered world simulation without native audio or real-time interactive steering.

What it unlocks

Creating real-time interactive worlds with native audio, physics, and human motion steered by text prompts.

What you need to act on it

  • research preview access
  • Google AI Ultra subscription
  • Gemini API early access
  • Google AI Studio early access

Send this to someone who needs it

Shares the story and its sources. Nothing about you.

What does this mean for your job?

This is the story as everyone gets it. Once a week we send you the version written for your role — what changed, why it matters for the work you actually do, and one thing to try. Free while we tune it.