Google just handed developers its world model: Genie 4 can now build playable 720p worlds with sound through the Gemini API
Genie 4 is now available to developers through the Gemini API and Google AI Studio, a day after launch. It generates explorable 720p worlds at 24fps with native audio from a text prompt, an image or both.
Google’s world model is no longer just a demo for subscribers. “Introducing Genie 4 in the Gemini API + @GoogleAIStudio, our first world model for developers to build with and create new world model experiences,” Google’s Logan Kilpatrick posted on X on Thursday.
What developers get
According to Google’s announcement, Genie 4 is available through the Gemini API, via its Interactions API, and in Google AI Studio. Developers can start from “a text prompt, a reference image, or both” and generate “continuous 720p worlds at 24fps with synchronized native audio”, from ambient sound to character dialogue.
Background
Earlier stories on this thread.
What happened next
Later stories on this thread.
The worlds are meant to be explored, not just watched. Google says you can move around with keyboard controls while typing live prompts that “change weather, lighting, objects, or events on the fly”, and that Gemini reasoning keeps the world consistent as it changes. Every output carries an invisible SynthID watermark.
Sundar Pichai pointed to the same feature when the model launched. “Really neat part of Genie 4 is you can type new prompts while exploring a generated world, like dropping in characters or changing the scene + the native audio adapts in real time,” he wrote on X. Until Thursday that experience sat inside Project Genie for eligible Google AI Ultra subscribers.
Why an API matters
A consumer demo shows what a model can do. An API lets other companies build products on it. Google lists prototyping interactive experiences, visualising spatial designs and “training robotics and AI agents” as uses. The last one matters most: a world model that can produce endless, controllable environments is cheap training ground for robots and software agents.
If you are new to the idea, our explainer on world models covers the basics, and our Genie 4 launch story has the earlier details.
What we don’t know yet
Google’s post points to a separate pricing page and does not quote prices in the announcement. It also gives no limit on session length. Developers trying it should check costs before building anything that runs for long sessions.
This report is not legal, financial, or health advice. See the disclaimer.
Primary sources
- Logan Kilpatrick on X: Introducing Genie 4 in the Gemini API + Google AI Studio Logan Kilpatrick on X
- Sundar Pichai on X: you can type new prompts while exploring a generated world Sundar Pichai on X
- Genie 4 is now available on the Gemini API Google