Google released Genie 4 on November 18, 2026, its most realistic and interactive world model yet, which turns a text prompt or an image into a world you can step inside, explore and change as you go. It arrived with a refreshed Project Genie experience for eligible Google AI Ultra subscribers, and a day later Google opened Genie 4 to developers through the Gemini API and Google AI Studio.
- Genie 4 lets you change a world while you are inside it: type a new prompt to shift the weather, add a character or redirect the action in real time.
- For the first time, Genie pairs its visuals with native audio that adapts to the scene, from background sound to character dialogue.
- Project Genie adds a creation agent and a community gallery where people can explore, remix and publish worlds.
- Developers can now build with Genie 4 in the Gemini API and Google AI Studio.
1. What is Genie 4?
Genie 4 is a world model from Google DeepMind: an AI system that generates interactive, explorable environments rather than fixed images or videos. You describe a place, or start from a reference image, and Genie 4 builds a world you can move through and interact with. Google calls it its most realistic and interactive world model so far, with its highest-fidelity visuals and physics.
The biggest change from earlier versions is control. You can type a new prompt mid-session and the world responds while you are still exploring it.
2. What is new in Project Genie?
Project Genie is Google's experimental space for creating and exploring these worlds in the browser, and this update makes it more responsive, creative and social. Alongside first-time access to Genie 4, Google added:
- The Project Genie agent: describe your idea in plain language and the agent uses Google's models to design the look of your world and a matching soundtrack.
- Gemini as a companion: Gemini can watch what is happening on screen, suggest where to go next, or trigger events as you explore.
- A community gallery: curated worlds and community creations you can explore, remix and build on, then publish your own.
- Genie 3 upgrades: sessions of up to three minutes per generation, the option to link worlds together, worlds seeded from 360-degree panoramas, and real-time events triggered by prompts.
Google showcased early creator collaborations in the gallery, including an interactive mystery set in a gothic manor and a photorealistic journey through an ant colony.
3. What can developers build with Genie 4?
Through the Gemini API and Google AI Studio, developers can generate continuous 720p worlds at 24 frames per second with synchronised native audio, starting from a text prompt, a reference image or both. Keyboard controls let users move through the environment while live prompts change the weather, lighting, objects or events, and Gemini reasoning keeps the world consistent as it evolves.
Google suggests uses such as prototyping interactive experiences, visualising designs for spatial concepts, and training robotics and AI agents. AI Studio includes an interactive canvas and starter apps to help developers begin.
4. Who can use Genie 4?
Genie 4 is available now to eligible Google AI Ultra subscribers in Project Genie, and to developers in the Gemini API and Google AI Studio. Google AI Pro members can join a waitlist for Project Genie. Every video and audio output carries Google's SynthID watermark, and inputs and outputs go through safety screening.
5. What does Genie 4 mean for marketers?
Genie 4 points to a new kind of content: interactive spaces people can explore, not just watch. A brand could prototype an explorable product setting or event space, test spatial concepts before building them, or create a playful experience that invites remixing. Because it is still an experimental research model, it is best treated today as a tool for prototypes and creative exploration.
- Bring ideas to life on the web: turn interactive concepts into fast, working pages with our web development team.
- Put AI to work: explore where generative AI fits your marketing with our AI marketing agency services.
- Stay current: follow the AI News hub for each new Google AI launch, including Gemini 4 Neon.
Frequently asked questions
What is Genie 4?
Genie 4 is a world model from Google DeepMind, released on November 18, 2026, that turns a text prompt or image into an interactive world you can explore and change in real time, with native audio that adapts to the scene.
What is Project Genie?
Project Genie is Google's experimental browser experience for creating, exploring and sharing interactive worlds. It now includes Genie 4, a creation agent, Gemini as an in-world companion, and a community gallery for remixing and publishing worlds.
Who can use Genie 4?
Eligible Google AI Ultra subscribers can use Genie 4 in Project Genie, Google AI Pro members can join the waitlist, and developers can build with it through the Gemini API and Google AI Studio.
Can developers use Genie 4 in the Gemini API?
Yes. Since November 19, 2026, developers can generate continuous 720p worlds at 24 frames per second with synchronised audio through the Gemini API and Google AI Studio, starting from text, an image or both.
More AI news
- GPT-6.2 Astra and Sol: OpenAI's New Models for Professional and Everyday Work
- Claude Meetings: An AI Meeting Assistant That Gets the Work Started
- Gemini 4 Neon: Frontier-Level Reasoning, Built for Speed
- ChatGPT Live Dictation: Your Words Appear as You Speak
- Anthropic IPO: The Company Behind Claude Lists on Nasdaq
- Gemini 4 Carbon: Google's Strongest Model for Agentic Work, Coding and Research
- Claude Fable 5.2 and Claude Mythos 5.2: Anthropic's Most Capable Models Get Faster and Smarter
- ChatGPT Wallet: How AI Agents Can Now Pay Securely on Your Behalf
- Gemini 4 Hydrogen in GitHub Copilot: General Availability Across 11 Developer Surfaces
- Claiming Google Developer Program Cloud Credits Directly in Google AI Studio
- Amazon Bedrock AgentCore Runtime V2: Architecture Patterns for Fast Session Startup
- Routing Coding Agent Requests on Amazon Bedrock with LiteLLM and NVIDIA NeMo Switchyard
- BigQuery Agent Analytics and Looker: Enterprise AI Agent Observability and Governance
- Microsoft Copilot Cowork, Projects and Workspaces: Unified Home, Skills and Automations
- Grok Bot 1.0: xAI's Multiplayer Team Bots for Slack, Microsoft Teams and Video Calls
- Claude Sheets, Claude Whiteboards and Claude Data: Collaborative Artifacts in Claude
- Google AI Search and Gemini 4 Hydrogen: Query Fan-Out and Visual Responses
- Businesses in ChatGPT: Business Hub, Engagement Insights and Business Agents
- Claude Plugins, Skills and Connectors: The New Plugins Page and Claude Marketplace
- ChatGPT Images 2.6: GIFs, Reference Images and What Marketers Should Know
- Google's Gemini Agent: What It Does, Coworker Agents and When You Can Use It