A new step in interactive AI experiences is taking shape as Google begins limited access to its experimental Project Genie, allowing users to generate playable virtual worlds directly within Gemini.
Months after previewing the Genie 3 artificial intelligence model, the Mountain View–based tech company announced that select premium Gemini subscribers can now create AI-powered, interactive environments using natural language prompts. The feature is built on the Genie 3 model and also uses Nano Banana and Gemini 3 to generate fully explorable virtual worlds. Genie 3 was first announced in August 2025.
According to a blog post by the company, Project Genie is currently available only to Google AI Ultra subscribers in the US who are above 18 years of age. Users can create, explore, and remix these virtual worlds. In the US, the Ultra plan costs $249.99 per month, while in India it is priced at Rs. 24,500 per month. However, the feature is not yet available in India.
Genie is a key project from Google DeepMind, which has developed 3 generations of large language models focused on virtual world creation. The company says this work supports its broader artificial general intelligence goals. Genie 3 is the most advanced version so far, capable of generating both 2D and 3D worlds. It can render scenes in real time as users move and interact, while maintaining realistic physics. Google says the technology has potential use cases in robotics, animation modelling, and related fields.
With Project Genie, users can type prompts or upload images to build interactive environments. They can also create characters and choose how to explore, including walking, riding, flying, or driving. A World Sketching feature powered by Nano Banana Pro allows detailed control over the environment.
The World Sketching tool lets users preview and refine worlds before entering them. Users can choose between first-person and third-person views. A Remix tool also allows them to expand or modify previously created worlds.
As the feature is still a research prototype, Google cautioned that worlds may not always closely match prompts or look fully realistic. Characters may sometimes be hard to control, and users could face higher latency. Each generated world is also limited to 60 seconds of exploration time.
Also read: Viksit Workforce for a Viksit Bharat
Do Follow: The Mainstream formerly known as CIO News LinkedIn Account | The Mainstream formerly known as CIO News Facebook | The Mainstream formerly known as CIO News Youtube | The Mainstream formerly known as CIO News Twitter
About us:
The Mainstream is a premier platform delivering the latest updates and informed perspectives across the technology business and cyber landscape. Built on research-driven, thought leadership and original intellectual property, The Mainstream also curates summits & conferences that convene decision makers to explore how technology reshapes industries and leadership. With a growing presence in India and globally across the Middle East, Africa, ASEAN, the USA, the UK and Australia, The Mainstream carries a vision to bring the latest happenings and insights to 8.2 billion people and to place technology at the centre of conversation for leaders navigating the future.
