Google has introduced Project Genie, an experimental artificial intelligence platform designed to generate interactive three-dimensional virtual worlds from simple text and image prompts. The tool, which is available to U.S. users subscribed to Google AI Ultra, represents an expansion of generative AI capabilities beyond static outputs such as text, images, and video. Project Genie is positioned as an early-access product, allowing users to explore the potential of immersive world-building through AI rather than as a mass-market release.
Project Genie is built on Genie 3, a world-model developed by Google DeepMind capable of dynamically generating environments in real time as users navigate them. Unlike traditional game engines such as Unreal or Unity, which require extensive asset creation, scene assembly, physics tuning, and scripting, Project Genie produces terrain, structures, and scenery on the fly. Users can walk, fly, or otherwise explore these environments, remix existing worlds, and export short video clips of their sessions. The system currently runs at approximately 720p resolution and 24 frames per second, with individual interactions limited to around one minute.
The tool combines three core capabilities: world sketching, world exploration, and world remixing. Users provide a short description of the environment and can optionally define an avatar, after which Project Genie generates an initial visual concept using Google’s image models and transforms it into a navigable 3D space. Google emphasizes that the platform is centered on interaction rather than passive viewing, enabling users to experience dynamic worlds in ways not possible with traditional static content creation tools.
Despite its potential, Project Genie remains clearly experimental. Google notes that generated worlds may not fully adhere to real-world physics or user prompts, character movement may be less controllable, and sessions are limited to 60 seconds. Access is currently restricted to U.S.-based subscribers of the Google AI Ultra plan, which costs $250 per month, approximately PKR 70,000, and includes benefits such as higher AI usage limits, 30 terabytes of cloud storage, and priority access to Google’s Antigravity agentic coding tool.
Project Genie reflects Google’s broader effort to expand the applications of AI into interactive and immersive experiences. By collapsing traditional game development steps into a single prompt, the platform allows creators to experiment with three-dimensional environments without prior technical expertise. Early access users have reported the ability to generate a wide variety of worlds and scenarios, highlighting the potential for education, entertainment, and creative exploration. While improvements are still needed, the prototype demonstrates a new direction for generative AI and its integration with interactive 3D spaces.
Follow the SPIN IDG WhatsApp Channel for updates across the Smart Pakistan Insights Network covering all of Pakistan’s technology ecosystem.
