LIVE

Google Expands Interactive World-Building with Genie 4 Launch

🤖 AI Models 2 min read 👁 0

Google has released its latest world-generation model, Genie 4, to premium AI Ultra subscribers, introducing real-time environment modification and audio integration.

Google Expands Interactive World-Building with Genie 4 Launch🤖AI Models

Photo: thenextweb.com

Key points

  • Genie 4 allows users to modify interactive worlds in real-time using text prompts.
  • The update introduces native audio, including background noise and dialogue.
  • All generated content is protected by Google's SynthID invisible watermarking.
  • Google DeepMind positions these models as potential training environments for future AI agents and robotics.

Google has officially launched Genie 4, its latest generative model designed to create interactive digital environments, for Google AI Ultra subscribers. The tool, accessible through the browser-based Project Genie platform, allows users to generate navigable worlds that can be modified mid-session through text prompts. This update marks a significant shift by introducing native audio capabilities, including ambient sound and character dialogue, to the immersive experience.

The release also includes a new creation agent capable of building worlds based on user conversation, alongside a community gallery for sharing and remixing projects. While Genie 4 offers enhanced interactivity, Google notes that the model remains a research prototype. Users may experience visual inconsistencies during extended sessions, and the system continues to face challenges with complex physics and legible text rendering.

To ensure transparency, all content generated within Project Genie is embedded with SynthID, Google’s proprietary invisible watermarking technology. Meanwhile, the previous iteration, Genie 3, remains available for users requiring longer generation windows, with its capacity extended to three minutes per session. Despite these advancements, industry adoption remains cautious, as major game developers continue to prioritize human-led design over generative alternatives.

What to watch next: As Google and competitors like Odyssey refine world models, the focus will shift toward whether these systems can reliably transition from creative prototypes to practical training environments for robotics and autonomous vehicles.

Source thenextweb.com — thenextweb.com/news/google-genie-4-project-genie-ai-ultra-world-model ↗

Contact the newsroom

Got a tip, a proposal or a partnership question? Write to us and we will reply shortly.