# Unite.AI — Google Brings Genie 4 to Project Genie for Eligible AI Ultra Users

- Company: Unite.AI (unite.ai)
- Announced: 2026-11-18T18:32:03+00:00
- Category: availability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.unite.ai/google-brings-genie-4-to-project-genie-for-eligible-ai-ultra-users/
- Record: https://forck.live/items/38160-google-brings-genie-4-to-project-genie-for-eligible-ai-ultra-users
- Subject: Reporting
- Models affected: Genie 4, Genie 3, Gemini Omni, Gemini 3.8 Flash

Google is rolling out a new Project Genie experience to eligible Google AI Ultra subscribers, giving them first-time access to Genie 4 inside the browser-based world-building prototype. Google AI Pro members can join a waitlist on the Project Genie site but are not part of the initial rollout. Genie 4 adds mid-session control: users can type prompts while navigating to change weather, add a character or object, move the camera or redirect events without starting over, and the model generates native audio with the visuals, including ambient sound, music and character dialogue. Google DeepMind describes Genie 4 as natively multimodal, with Gemini Omni providing a real-world reference for how simulations look and behave and other Gemini models supplying reasoning for coherence and continuity. The rollout follows Google DeepMind's October 27, 2026 research-preview announcement, which named Ultra subscribers in Project Genie as a next release group. Google positions Genie 4 as its higher-fidelity option for visuals, physics and native audio, while Genie 3 remains selectable for longer runs or worlds seeded from 360-degree panorama images; Genie 3's per-generation limit is now three minutes, up from 60 seconds. All video and audio generated in Project Genie include SynthID, and Google says both Genie models remain frontier research systems, with camera latency, intricate physical interactions, real-time audio precision and long-term scene permanence unresolved.

## Evidence

Verbatim from https://www.unite.ai/google-brings-genie-4-to-project-genie-for-eligible-ai-ultra-users/:

> Genie 4 lets users reshape weather, characters and events mid-session without restarting the simulation.
> 
> Gemini models supply real-world reference and in-loop reasoning that keep Genie 4 simulations coherent.
> 
> Persistent scene drift and camera latency remain the main limits on longer Genie 4 creative sessions.
> 
> Google announced on November 18, 2026 that a new Project Genie experience is rolling out to eligible Google AI Ultra subscribers, opening first-time access to Genie 4 within the browser-based world-building prototype alongside a conversational creation agent and community gallery.
> 
> Google AI Pro members can join a waitlist on the Project Genie site, but are not part of the initial rollout.
> 
> Genie 4 adds control during a session. Users can type prompts while navigating to alter weather, add a character or object, move the camera or redirect events without starting over. The model also generates native audio with the visuals, including ambient sound, music and character dialogue that reacts to user inputs and events in the simulation.

---

Record: https://forck.live/items/38160-google-brings-genie-4-to-project-genie-for-eligible-ai-ultra-users
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
