Google Rolls Out Genie 4 in Project Genie for AI Ultra

This article contains no affiliate links. How this article was prepared: AI helped gather and draft this research; a person checked the facts against the cited sources.

Quick answer

Google is rolling out a new Project Genie experience to eligible Google AI Ultra subscribers, with first-time access to Genie 4, which Google says can generate more realistic virtual experiences. Genie 4 lets you prompt mid-session to change a world — shifting the weather, dropping in a character or redirecting the action — with real-time native audio. Genie 3 now runs for up to 3 minutes per generation, and a new Project Genie agent and a community gallery round out the update.

Genie 4 comes to Project Genie

Google's Genie 4 model is now available to eligible AI Ultra subscribers in Project Genie, The Verge reports. Google first announced Genie 4 on October 27, 2026, and initially released it to trusted testers late last month.

The update unlocks first-time access to Genie 4 in Project Genie. Google says Genie 4 unlocks unprecedented realism and improves real-time interactive simulation.

What Genie 4 does

With Genie 4, you can now prompt mid-session to change the world you created. Just type a new prompt while you navigate your world and you can edit your environments in real time. Shift the weather, drop in a character, or redirect the action.

Genie 4 is natively multimodal, enabling audio-like music, ambient noises, and interactive dialogue to be simultaneously generated with the world.

Genie 3 gets longer runs and linked worlds

Today's Genie 3 updates include longer sessions and linked worlds. Explore for up to 3 minutes per generation (up from 60 seconds), or link multiple worlds together for longer journeys.

You can also seed new worlds from 360-degree panorama images, and dynamically change the environment with natural-language prompts while you explore, according to Google's blog post (https://blog.google/innovation-and-ai/models-and-research/google-deepmind/genie-4-now-available-project-genie/).

An agent and a gallery

The new Project Genie agent takes creation beyond a single text or image prompt. Describe your vision in natural language, and the agent orchestrates Google's suite of multimodal models to craft the world's signature look, paired with custom background scores tailored to the mood, according to Google's blog post (https://blog.google/innovation-and-ai/models-and-research/google-deepmind/genie-4-now-available-project-genie/).

The new Project Genie gallery brings together a rich collection of curated worlds alongside creative work from the community, and you can publish your creation to the community gallery for others to explore and remix, according to Google's blog post (https://blog.google/innovation-and-ai/models-and-research/google-deepmind/genie-4-now-available-project-genie/).

Who can use it, and the limits

Project Genie is available to Google AI Ultra subscribers. Google AI Pro subscribers can join a waitlist, and access will be granted gradually based on availability. You must be 18 years of age or older. Daily usage limits apply and may vary by plan and demand.

DeepMind lists Genie 4's known limits: the model currently supports around a minute of continuous interaction, rather than extended sessions. Visual details and object permanence can shift or drift over time. Clear and legible text is often only generated when it's in the input world description.

All video and audio generated by Genie 4 will include SynthID.

FAQ

Who can use Genie 4 in Project Genie? Project Genie is available to Google AI Ultra subscribers. Google AI Pro subscribers can join a waitlist, and access will be granted gradually based on availability.

What can you change mid-session in Genie 4? You can prompt mid-session to change the world you created: shift the weather, drop in a character, or redirect the action.

How long can Genie 3 run now? Explore for up to 3 minutes per generation (up from 60 seconds), or link multiple worlds together for longer journeys.

What does the Project Genie agent do? It builds worlds from a natural-language conversation: describe your vision, and the agent orchestrates Google's multimodal models to craft the world's look and background score, according to Google's blog post (https://blog.google/innovation-and-ai/models-and-research/google-deepmind/genie-4-now-available-project-genie/).

What are Genie 4's known limits? Around a minute of continuous interaction; visual details and object permanence can shift or drift over time; clear and legible text is often only generated when it's in the input world description.

Is Genie 4's output watermarked? All video and audio generated by Genie 4 will include SynthID.

Sources

Google, "Genie 4 is now available", November 18, 2026: https://blog.google/innovation-and-ai/models-and-research/google-deepmind/genie-4-now-available-project-genie/

Google DeepMind, "Genie 4: A new generation of world simulation", October 27, 2026: https://deepmind.google/blog/genie-4-a-new-generation-of-world-simulation/

Google DeepMind, Genie model page: https://deepmind.google/models/genie/

Google Labs Help, "Get started with Project Genie": https://support.google.com/labs/answer/16875695?hl=en

The Verge, "Google is rolling out its latest AI world model more widely", Jay Peters, November 18, 2026, 6:36 p.m. UTC: https://www.theverge.com/tech/1036897/google-is-rolling-out-its-latest-ai-world-model-more-widely

Google DeepMind on X: https://x.com/GoogleDeepMind/status/2123117733709586849

Get new free-deal guides & reviews by email

Leave a Comment