Google has announced a new AI model, Genie 4, “which unlocks unprecedented realism and improves real-time interactive simulation.”
Google has been playing catchup to Anthropic and OpenAI, with its Gemini models often lagging behind in capability. Until recently, Google’s models were largely competing on price and efficiency. Recently, however, Google has made major strides toward closing the gap with its Gemini 4 Argon model, announced at the end of September.
The company may have closed the gap altogether with Genie 4, its new world model. The company says Genie 4 is “natively multimodal, enabling audio-like music, ambient noises, and interactive dialogue to be simultaneously generated with the world.”
In the race to AGI (artificial general intelligence), understanding how the world works is a critical step, and one that traditional LLMs have struggled with. Genie 4 is designed to further advance that understanding.
Understanding and simulating the world is a crucial aspect of building AGI. Genie 4 advances our ability to create safe, infinitely variable simulations that can help with everything from developing training environments for robots and agents to unlocking the creation of new interactive experiences.
That focus on understanding the world and improving world simulations shows itself in four specific areas:
Shaping world simulation in real-time
With Genie 4, you can use natural language to modify a simulation in real-time — like changing the weather, moving the camera, or introducing a new person or object — and Gemini will contextually adapt your prompt to match the surrounding scene. Between your inputs, Gemini also monitors and steers the scene to keep the world progressing cohesively.
Pushing the frontier in realism for physics and human action
Genie 4 introduces a new standard of realism to real-time interactive simulation. Built on an advanced physical understanding of the world, Genie 4 simulates real-world physics scenarios, such as aerodynamics, collisions, and more.
The most dramatic leap is how Genie 4 simulates people, creating characters that move naturally, respond organically to their environments, and can be interactively steered in real-time.
Modeling how the world sounds
Genie 4 is our first real-time world model to generate audio natively. Every world carries the ambient sound of its own setting, from wind in the trees to waves crashing at the beach.
The true frontier, however, is human speech. Genie 4 introduces interactive dialogue that adapts on the fly. Characters converse and react to your inputs or events in the world, all in real-time.
Simulating complex events with Gemini models
Bringing Gemini and Genie 4 together adds a new layer of reasoning to world simulation, allowing us to model complex, multi-step events and test how AI systems navigate different environments before bringing them to the real world.
To achieve this in real-time, Gemini 3.8 Flash serves as a guiding agent in the loop: as Genie 4 generates a world in real-time, Gemini continuously observes the scene, breaks down goals into a sequence of steps, and reviews incoming frames to track the progress and verify that each step succeeded. As the world shifts or the user intervenes, Gemini adapts its plan in the moment, unlocking worlds with reliable causality, procedural behaviors, and multi-step reasoning.
Much like Anthropic and OpenAI with their most advanced models, Google is restricting access to Genie 4 for now. The company is rolling it out as a research preview for trusted testers, gathering feedback before it releases the model more broadly.
Once Google is ready to release Genie 4 to a wider audience, it will come first to Google AI Ultra subscribers in Project Genie, as well as Gemini API and Google AI Studio early access partners.