A day after Genie 4 launched, Google has opened the world model to developers through the Gemini API, via the Interactions API, and in Google AI Studio.

Starting from a text prompt, a reference image, or both, developers can generate continuous 720p worlds at 24 frames per second with synchronized native audio, from ambient soundscapes and sound effects to character dialogue. Real-time keyboard controls work alongside live text prompts, so you can navigate environments and change the weather, lighting, objects or events as you go, while Gemini reasoning keeps the world state consistent and coherent throughout.

Google pitches it as a blank canvas for prototyping interactive experiences, visualizing designs for spatial concepts, or training robotics and AI agents. Every output includes imperceptible SynthID watermarking.

An interactive canvas and starter apps are available in Google AI Studio, with pricing details and API documentation linked from the announcement for developers ready to start building.