Radar / AI media tools / Google Genie 4

Google Genie 4: real-time world model with native audio and live steering

Google DeepMind announced Genie 4 on 27 Oct 2026: a world model that generates photorealistic, interactive 3D worlds in real time from a text prompt or image, with natively generated audio — music, ambient sound, and character dialogue — plus live steering via natural-language prompts mid-simulation. Coherent scenes last up to about two minutes, double Genie 3's limit, with Gemini models anchoring realism and guiding multi-step events inside the simulation loop. It is in research preview for trusted testers, with rollout to Google AI Ultra subscribers via Project Genie and to Gemini API / AI Studio early-access partners to follow.

new launchmedia · 3dJEV traction 0.62added 2026-10-28

Open Google Genie 4 →View on the radar

Why it matters

The first real-time world model where sound is generated in the same loop as the visuals, and where the world can be steered live — characters that talk back and scenes that change as they run, not just clips that play.

What you could build with it

A game studio prototyping a new level could generate a playable draft world from a text prompt, walk through it with keyboard controls, and steer weather, characters, and camera live to test a scene's feel before committing artists to building it.

Does it hold up?

Too early to judge: research preview limited to trusted testers, so no independent hands-on evidence exists yet, and DeepMind itself flags drift over longer sessions and after repeated edits.

Built with Google Genie 4

Google's Genie 4 world model adds audio, more realistic worlds, and real-time steeringarticle · TechCrunch launch coverage: native audio, free-form mid-simulation edits, two-minute scene consistency, and the Gemini Robotics simulation experiment.
Google's Genie 4: Interactive Worlds Now Talk Back, and You Can Steer Them Livearticle · Hands-on-style explainer: sound, two-minute duration, and live steering as the three changes, with DeepMind's own caveats on drift after repeated edits.
Meet Google DeepMind's Genie 4: Real-Time World Model With Native Audioarticle · MarkTechPost overview: Gemini inside the simulation loop as planner, Google-hosted access only, and sessions lasting a few minutes with drift as the main limit.

Learn more

official announcement →

First spotted on article: source.

More AI media tools

VoiceStudio — open-source, fully-local ElevenLabs alternativeOpen-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation…media · JEV 0.73OpenMontage: open-source agentic video production systemTurns an AI coding assistant into a full video studio: 12 pipelines and 100+ tools for scripting, footage, narration…media · JEV 0.73Video Shotcraft: AI video skill for Claude Code & Codex that directs cinematic product promos in RemotionA skill package for Claude Code and Codex that turns a product brief into a finished promo video: the agent captures…media · JEV 0.71Lemo-Opuscar: 59 code-directed film styles for Claude CodeA toolbox of 59 film styles, each a style prompt plus a demo film made entirely in code by Claude Opus 5.5 with no…media · JEV 0.71LingBot-Map: streaming 3D reconstruction foundation model (ECCV 2026 best-paper candidate)Feed-forward 3D foundation model that reconstructs scenes from streaming video at ~20 FPS with drift correction over…media · JEV 0.7HyperFramesHeyGen's open-source framework that turns HTML/CSS/GSAP into deterministic MP4 video via 21 agent skills and a router…media · JEV 0.69

Get the week's best AI launches, plus 3 ideas worth building

One email every Saturday. Ranked by traction, not hype. Free.