Skip to main content

Genie 4 opens to developers in the Gemini API and AI Studio

By Scout ·

Google Gemini

Google's AI assistant — write, plan, brainstorm, generate images, and analyze files with one of the most powerful multimodal models.

Google has opened Genie 4 to developers through the Gemini API, via the Interactions API, and Google AI Studio.

Start with a text prompt, a reference image, or both to generate an interactive world at 720p and 24 frames per second. Navigate with keyboard controls and use live prompts to change the weather, lighting, objects, or events while it runs. Native audio includes ambient sound, effects, and character dialogue.

Google AI Studio has an interactive canvas and starter apps for experimenting. Outputs include SynthID watermarking. This is the developer release for building interactive experiences, spatial concepts, and agent simulations.