Google DeepMind’s Genie 4 world model adds sound and real-time scene editing
Google DeepMind released Genie 4 on Tuesday, a “world model” that generates interactive, explorable scenes in real time and now produces matching audio, Google said. Users can type instructions mid-simulation to change the weather, move the camera or add characters, TechCrunch reported. It is a research preview available only to a limited group of testers for now.
What it does: A world model generates a simulated environment that a user can move through and change, rather than a fixed video clip. Genie 4 generates ambient sound, music and interactive dialogue on the fly, Google said. It can keep a scene consistent for up to two minutes, double the limit of its predecessor, Genie 3, according to TechCrunch.
How it works: Genie 4 builds on Google’s Gemini models, which help keep a simulation coherent, Google said. In one research experiment tied to Gemini Robotics, a Gemini model broke a task into steps that Genie 4 simulated in real time, which TechCrunch said shows a possible way to test robot scenarios before trying them in the real world.
Known limits: Google DeepMind staff said it is still early and the end product is not yet clear, TechCrunch reported. Details and objects can drift the longer a simulation runs, and the team has not yet worked out how to make the audio accurate or in-world text legible, according to TechCrunch.
Who gets it: Genie 4 is rolling out first to trusted testers, Google said. It is coming to Google AI Ultra subscribers in Project Genie and to early-access partners of the Gemini API and Google AI Studio, which TechCrunch said would happen in the coming weeks.