Google is rolling out a new Project Genie experience to eligible Google AI Ultra subscribers, giving them first access to Genie 4, a world model that generates interactive environments users can change with text while exploring them.
Announced on November 18, Genie 4 is what Google calls its most realistic and interactive world model yet. Users can type new prompts mid-session to shift the weather, add a character or redirect the action, and for the first time the visuals come with native audio generated in real time, from ambient sound to character dialogue.
Genie 3 stays in the model picker with upgrades: sessions of up to 3 minutes per generation, up from 60 seconds, the ability to chain worlds together, and worlds seeded from 360-degree panoramas. One of Google’s demos is built from a panorama of Petra in Jordan.
A new Project Genie agent builds worlds from a natural-language description, using Google’s multimodal models for the look and a matching soundtrack, and a community gallery lets people publish and remix creations. Google says all generated video and audio carries SynthID watermarks and that the models remain research-stage, with open issues such as camera latency, complex physics and long-term scene permanence. Google AI Pro members can join a waitlist.
Why it matters
World models are moving from research demos into a paid product, hinting at new tools for game design, education and simulation without code. Access is still limited to Google’s top-tier plan and to eligible subscribers, so users in the Arab region should check availability in their country before signing up.
Source: Google Blog
By the TechMojaz team

اترك تعليقاً