Google makes Genie 4 available to developers in the Gemini API and AI Studio
Google says Genie 4, its interactive world model, is now available to developers through the Gemini API (via the Interactions API) and Google AI Studio. Its post follows what it calls "yesterday's Genie 4 launch"; the model was first announced on October 27 for trusted testers and early-access partners.
According to Google, developers can start from a text prompt, a reference image, or both, and generate continuous 720p worlds at 24 fps with synchronized native audio, including ambient sound, sound effects and character dialogue. Real-time keyboard controls and live text prompts let users move through an environment and change weather, lighting, objects or events as it runs. Google says Gemini reasoning keeps the world state consistent, and that every output carries an imperceptible SynthID watermark.
Google suggests uses such as prototyping interactive experiences, visualizing spatial designs, and training robotics and AI agents. AI Studio offers an interactive canvas and starter apps; pricing and API documentation are linked from the post.
Sources
- Genie 4 is now available on the Gemini API.antigravity
Get news like this as a push.
AI Tracker alerts you when something changes for the tools you use.