Launches
Genie 4 gives interactive AI worlds a voice and lets you rewrite the scene live
Developing 1 source
Google DeepMind's experimental interactive world model with native audio, live text steering and Gemini-guided simulation.
What happened lately
Google DeepMind announced Genie 4 on October 27, 2026, as a research preview for trusted testers. It generates interactive visual worlds and accompanying audio, with text prompts and Gemini models helping steer unfolding scenes. Google AI Ultra access through Project Genie and early access through the Gemini API and Google AI Studio are described as coming soon. The announcement acknowledges drifting visual details, imperfect physics and limits to long-term consistency.