Google Genie 4 World Model
In brief
Genie 4 is an advanced world model empowering you to generate, step inside, and shape worlds directly from your browser 1. You can use natural language prompts to edit environments in real time and add native audio 1.
Who can use it
We are rolling out Genie 4 to eligible Google AI Ultra subscribers 1. Google AI Pro members can join the waitlist on the same page 1.
Does this affect you?
- DevelopersYou can use prompts as repeatable seeds for everything from creative prototyping to robotics training environments 4.
- Product managersYou can collaborate with creative agents and multimodal models to test interactive user experiences quickly 1.
- FoundersYou can build interactive prototypes and custom simulations directly from your browser without complex software 1.
- Everyday usersYou can explore curated worlds, transform personal photos into spaces, and remix environments using simple text 1.
How to start
Eligible Google AI Ultra subscribers can try the new Project Genie experience starting today 1, but formal setup instructions are not published.
What you can build
Before you rely on it
- The model remains in the frontier research space with challenges like camera latency and intricate physical interactions 1.
- Access is currently restricted to Google AI Ultra subscribers while Pro members must join a waitlist 1.
- All generated video and audio include SynthID watermarking and safety screenings 1.
Quick check
3 questionsAvailability
Sources
4 merged into this cardMore from Google

Gemini 4 Neon
Google's new Gemini 4 model pairs a 1M-token context window and four thinking levels with lower cost per task. It scores 61 on the AA Intelligence Index and targets complex coding, analysis, and cyber workflows.
Google updates Genie 3 model
Google has updated the Genie 3 world model with 3-minute sessions, world chaining, 360-degree panorama grounding, and real-time promptable events.