What is new
Genie 4 is described as a world model. According to the announcement, a user sets an event in motion and the model simulates what comes next. Google DeepMind says the release brings enhanced photorealism, fluid movement and native audio.
The company says this is its first real-time world model to generate audio natively. All the sounds in the announcement post were produced directly by Genie 4, per the post. It also introduces interactive dialogue that adapts on the fly.
How the Gemini models fit in
Google DeepMind says Genie 4 incorporates and builds on capabilities from the Gemini family. Gemini Omni anchors the simulations in real-world appearance and behavior, while other Gemini models supply reasoning meant to keep a simulation coherent and continuous.
Users navigate and control the camera with standard keyboard controls, and use text prompts to steer the scene as it evolves. They can also modify a simulation in real time using natural language, and Gemini adapts the prompt to match the surrounding scene.
What it means for creators and sellers
For people who make short video and product clips, a model that carries picture and sound together may reduce the number of separate steps in a workflow. It could be worth watching if you already storyboard scenes or build demo footage by hand.
Google DeepMind did not say who can use Genie 4, where, or at what price. It also did not say whether this is a public release or a demonstration, or when access might open. Until those details are shared, treat Genie 4 as something to test later, not a tool to plan work around.
How this was made: the text was written by AI from the source material, checked against the source and reviewed by an editor. The illustration was generated by AI for AISTETIKA and is not a frame from the story.
