Skip to content
Moojaz — موجز
Search
Menu
HomeRegionsMaghrebAfricaMiddle EastEuropeAsiaAmericasWorldSectionsPoliticsEconomySecurityHealthScienceTechnologyAIEnvironmentCultureSportsSearch
File

Google's Genie 4 interactive simulations

This dossier follows Google DeepMind's interactive simulations and access conditions for Genie 4.

Last updated : 1 key moments
Google DeepMind logo
Google DeepMind logo, used for identification. — DeepMind Technologies Limited (Alphabet), Wikimedia Commons — domaine public (PD-textlogo).

Where things stand

As of 28 October 2026, Google has announced a preview for selected testers.

Reported information

Google previews Genie 4 interactive simulations with native sound

Google DeepMind announced a research preview of Genie 4 on 27 October 2026. Access is restricted to selected testers; the model is not yet generally available.

Google DeepMind logo
Google DeepMind logo, used for identification. — DeepMind Technologies Limited (Alphabet), Wikimedia Commons — domaine public (PD-textlogo).

Google says users can explore a generated environment and change a running scene with written instructions: altering the weather, moving the camera or adding a character. The model also generates ambient sound, music and dialogue.

Google plans subsequent access through Project Genie for AI Ultra subscribers and selected Gemini API and AI Studio partners. It has announced no general release timetable or Genie 4-specific price. The proposed uses, including interactive creation and training robots or agents, remain applications put forward by the laboratory.

Sources 3