Google announced Genie 4, its latest world model for generating interactive AI experiences. According to the company, the model introduces four main updates: more realistic worlds, the ability to update an experience in real time using natural language prompts, audio generation, and the use of Gemini 3.8 Flash to support its simulations. Genie 4 can create experiences roughly two minutes long, up from one minute in the previous Genie 3 model.
Google positions the model as useful for pre-visualization in filmmaking, prototyping game concepts, and building training scenarios for robots.
Why it matters
Longer durations, real-time edits, and audio generation expand what interactive AI world models can produce, moving them closer to practical use in creative and simulation workflows.
Who should care
Filmmakers, game developers, and teams working on robot training scenarios are the audiences Google identifies as potential users.