Google has unveiled Genie 4, a new world model designed to generate interactive AI experiences. The updated system features four primary enhancements, including improved visual realism and the ability to modify environments in real time using natural language prompts.
The model now incorporates audio generation capabilities and utilizes the Gemini 3.8 Flash architecture to support its simulations. These technical upgrades allow the platform to produce interactive content lasting up to two minutes, doubling the duration of the previous Genie 3 version.
Google suggests the tool could be applied to film pre-visualization, game prototyping, and the creation of robot training scenarios. However, the company notes that longer simulations may experience shifts in object permanence and detail consistency over time.
Genie 4 is currently available as a research preview for a select group of trusted testers. The company has opened a waitlist for broader access and plans to release the model to Google AI Ultra subscribers in the near future.
