Google unveils Genie 4 for creating interactive AI worlds

Google has unveiled the Genie 4 model, which allows the creation of interactive explorable worlds, equipped with audio and dialogue, with the ability to edit scenes in real time using text commands.

According to the company, the model allows users to explore and interact with virtual environments, while generating music, ambient sounds, and interactive dialogue in sync with the scene. They can also guide the simulation as it plays using natural language, such as changing the weather, moving the camera, or adding new characters and elements.

The scene can be controlled using a keyboard and mouse, while the Gemini 3.8 Flash model acts as a guide in following the scene, breaking down subjects into steps, reviewing successive frames to check progress and adjusting the plan when changes or user intervention occur.

Compared to the previous model Genie 3, the Genie 4 offers greater visual realism and smoother movement, along with improved simulation of physics, human characters, and integrated sound generation.

The model can maintain the consistency of the scene for up to two minutes, twice as long as the previous model.

The model can be used to develop game ideas, interactive learning, pre-visualize cinematic scenes, and create simulation environments to train robots and intelligent agents. In one demo, Gemini 4 Argonne and Genie 4 worked to simulate a humanoid robot from Aptotronic playing a game of checkers, by breaking down the task into steps that are represented in the simulation in real time.

Google explained that the model is still in the experimental research phase and has been made available to a limited group of trusted testers, and will later expand its reach through the Google AI Ultra service, Project Genie, Gemini API and Google AI Studio environments.

The model still faces research challenges, including maintaining the consistency of details and objects over time, the accuracy of physical and sound interactions, the readability of text, and the spatial accuracy and continuity of the scenes.

About Qatar Living:

Since 2005, Qatar Living has been the trusted destination for everything Qatar. As the country's largest online community and marketplace, Qatar Living connects people with opportunities through jobs, property, vehicles, services, classifieds, events, local insights, and breaking news. Trusted by residents, newcomers, visitors, and businesses alike, Qatar Living brings Qatar together in one place.

Instagram - @qatarliving

X - @qatarliving

Facebook - Qatar Living

YouTube - qatarlivingofficial