Own a mobile shop? Open your free online shop in 5 minutes

Google opens Project Genie with Genie 4 to Ultra subscribers

2 min read
Google opens Project Genie with Genie 4 to Ultra subscribers
Project Genie now lets Google AI Ultra subscribers create interactive 3D worlds with real-time editing, native audio, and a community gallery for sharing and remixing.

What is new

Google DeepMind has rolled out a major update to Project Genie, its experimental platform for generating and exploring interactive digital worlds. The new experience, available to eligible Google AI Ultra subscribers, introduces Genie 4 — the most realistic and interactive world model yet — along with a conversational creation agent, real-time audio, and a community gallery for sharing and remixing worlds. Google AI Pro members can join the waitlist.

Real-time world editing with Genie 4

With Genie 4, you can now modify environments in real time using natural language prompts while navigating your world. Type a new prompt mid-session to shift the weather, drop in a character, or redirect the action. For the first time, Genie 4 pairs these visuals with real-time native audio that adapts as the scene unfolds — from ambient soundscapes to character dialogue. This makes worlds feel alive and responsive in a way previous models couldn't achieve.

Genie 3 gets longer sessions and panorama grounding

While Genie 4 delivers the highest-fidelity visuals and audio, Genie 3 remains available for longer runs. Today's updates to Genie 3 include extended sessions up to 3 minutes per generation (up from 60 seconds), the ability to link multiple worlds together for longer journeys, and 360-degree panorama image grounding to seed new worlds from panoramic photos. Real-time promptable events let you dynamically change the environment with natural language while exploring.

Build worlds through conversation with the Project Genie agent

The new Project Genie agent takes creation beyond a single text or image prompt. Simply describe your vision in natural language, and the agent orchestrates Google's multimodal models to craft initial visuals establishing your world's signature look, paired with custom background scores. You can bring Gemini models into the session as you explore — they observe what's happening on screen, surface context-aware suggestions for where to go next, or trigger in-world events automatically as your journey unfolds.

Community gallery for sharing and remixing

The new Project Genie gallery brings together curated worlds alongside community creations. Featured experiences include "Villa Giallo," a gothic manor mystery built with creative technologist Will aka BLVCKL!GHT, and "The Life of Ants," a photorealistic ant colony perspective built with filmmaker Anand Gandhi. You can launch your vision with a simple prompt, remix existing gallery experiences by tweaking the underlying world structure, soundtrack, or rules, and publish your own creations for others to explore and remix.

Responsible development and access

All video and audio generated in Project Genie includes SynthID watermarking, and all model inputs and outputs go through safety screenings. Genie 3 and Genie 4 remain world models in the frontier research space, with ongoing work on camera latency, intricate physical interactions, real-time audio precision, and long-term scene permanence. Eligible Google AI Ultra subscribers can try the new experience starting today; Google AI Pro members can join the waitlist on the Project Genie website.

Found this useful?

Share it with someone shopping for a phone.

Keep reading

All articles