🔍 Read the full analysis: Google Genie 4: A Tour Of Its AI Worlds And Their Limits on ThorstenMeyerAI.com
Get the latest gadgets delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
TL;DR
Google DeepMind presented Genie 4 on October 27, describing a real-time world model that generates interactive scenes, sound and changes prompted by text. The demonstrations are company-selected, the system is not generally available, and DeepMind says objects and details can drift during sessions lasting a few minutes.
Google DeepMind demonstrated Genie 4 on October 27, presenting an AI system that generates interactive scenes users can move through and alter with text prompts. The company says it can produce sound alongside visuals and respond while a scene is running, but the model is not yet broadly available and its worlds can drift after a few minutes.
DeepMind describes Genie 4 as a world model: rather than rendering a completed video or drawing from a prebuilt 3D map, it predicts the next frames in response to what a user does. In the company’s demonstrations, users move with keyboard and mouse controls and enter directions such as changing the weather or adding an object. DeepMind says the model can adapt those instructions to the scene.
The company also says Genie 4 generates audio in real time, including environmental sounds, music and character dialogue, and simulates events such as collisions and aerodynamics. DeepMind says Gemini 3.8 Flash can help interpret goals, divide them into steps and monitor the generated scene. These descriptions come from DeepMind; its announcement did not include benchmark results or independent tests.
DeepMind says access will begin with trusted testers. It plans to make the system available soon to Google AI Ultra subscribers through Project Genie and to early Gemini API partners. The announcement supplied no launch date or API pricing. TechCrunch and Bloomberg, as cited by heise, reported demonstrations of up to about two minutes, while DeepMind’s own description says interaction lasts “a few minutes.”
Infographic 01 · How Genie grew up
From flat sketches to worlds with sound, in under three years.
Each step as Google DeepMind described it. Session limits and consistency are different measures, so read the labels.
- Feb 2024
Genie 1Simple 2D worlds11 billion parameters, learned from unlabelled internet videos - Dec 2024
Genie 23D worlds from a single imageConsistent “for up to a minute”; real time only as a slimmed-down, lower-quality version - Aug 2025
Genie 3First real-time Genie720p at 24 frames per second, consistent “for a few minutes”, memory about one minute back - Jan 2026
Project GenieUS AI Ultra subscribers can play60 seconds per world, partly because of compute costs - May 2026Project Genie goes globalIn the $200 AI Ultra tier, for users 18 and older
- 27 Oct 2026
Genie 4Sound, live steering, more realismResearch preview for trusted testers; Ultra subscribers and API partners “coming soon”
Genie 3 vs. Genie 4
As described by Google DeepMind. Genie 4 column = vendor claims unless marked.
| Feature | Genie 3 (Aug 2025) | Genie 4 (Oct 2026) |
|---|---|---|
| Sound | Genie 3: None | Genie 4: Generated with the picture: ambient noise, music, dialogue |
| Steering | Genie 3: Keys, plus “promptable world events” | Genie 4: Free-form text changes while it runs; Gemini adapts and checks them |
| Look | Genie 3: 720p, 24 fps | Genie 4: “Unprecedented realism”; no resolution or frame rate published |
| How long | Genie 3: “A few minutes”; Project Genie capped at 60 s | Genie 4: “A few minutes” (DeepMind); up to ~2 min consistent scene reported |
| Access | Genie 3: Small preview, then Project Genie | Genie 4: Trusted testers; Ultra and API partners “coming soon” |
Sources: Genie paper, arXiv, 23 Feb 2024; Genie 2 blog, 4 Dec 2024; Genie 3 blog, 5 Aug 2025; TechCrunch, 29 Jan 2026; Google, 19 May 2026; Google DeepMind, Genie 4 blog, 27 Oct 2026; Genie 4 model page (limitations, disclaimer); TechCrunch, 27 Oct 2026. Table wording: Thorsten Meyer.
Powered by Thorsten Meyer AI
Where Interactive AI Could Be Used
If the capabilities hold up beyond selected demonstrations, Genie 4 could let creative teams test settings and interactions without building a conventional game environment for every idea. DeepMind reports tester feedback describing uses in film previsualization and game prototyping. Those are reported examples, not evidence of established commercial workflows or measured productivity gains.
The system also points to a possible research use: generating simulated situations for robotics. DeepMind showed a demonstration involving Apptronik’s Apollo humanoid, but the report describes it as a simulation, not a test with a physical robot. That distinction matters because generated scenes may not reliably reproduce the real-world physics and conditions that robot training requires.
For viewers, increasingly realistic generated scenes and matching audio may make synthetic media harder to recognize by sight and sound alone. DeepMind says Genie 4’s video and audio outputs carry an invisible SynthID watermark. How reliably that marking can be detected or retained in downstream use was not established in the material provided.
Products Worth Considering
Logitech MX Keys S Wireless Keyboard, Graphite
Logitech MX Mechanical Wireless Illuminated Keyboard, Tactile Quiet, Graphite
Bose QuietComfort Wireless Bluetooth Headphones with Active Noise Cancellation, Mic, USB‑C Charging, Deep Bass, 24‑Hour Battery – White Smok
As an affiliate, we earn on qualifying purchases.
Genie’s Move Toward Real-Time Worlds
Genie 4 follows several generations of work. DeepMind’s first Genie, introduced in February 2024, generated simple 2D worlds; its research paper described an 11-billion-parameter model trained on unlabeled internet videos. Genie 2, announced in December 2024, created 3D worlds from a single image and could maintain them for up to a minute, though real-time use required a lower-quality version.
In August 2025, DeepMind presented Genie 3 as its first real-time world model, running at 720p and 24 frames per second. The company said its scenes remained consistent for a few minutes, with visual memory reaching back about one minute. Google opened Genie 3 through Project Genie to paying U.S. subscribers in January 2026. TechCrunch reported a 60-second limit per world, partly tied to computing costs.
Genie 4’s announced additions are therefore not just more detailed imagery: DeepMind says it combines live interaction, generated audio and text-directed changes. The available evidence remains company demonstrations and reported tester feedback, rather than published comparative benchmarks.
“Details and objects can shift or drift over time.”
— Google DeepMind
Access, Consistency and Proof
Several points remain unresolved. DeepMind has not published a public release date, API price or benchmark results, and access is currently limited to trusted testers. The exact session limit is also unclear: DeepMind says “a few minutes,” while TechCrunch and Bloomberg, as cited by heise, report scenes of up to about two minutes.
The examples shown were selected by DeepMind, and there is no independent evaluation in the supplied material establishing how often the system follows prompts, maintains continuity or reproduces realistic physics. DeepMind itself warns that objects and details can drift. The robotics example did not involve a real robot, and the reported creative uses are tester feedback rather than published outcome data.
The Next Test Is Wider Access
The next stated step is access for trusted testers, followed by a planned rollout to Google AI Ultra subscribers through Project Genie and early Gemini API partners. DeepMind has not given dates for those stages or said when access will expand further.
Broader testing will show whether users can reliably control scenes beyond short, company-produced clips, and whether the audio and visual consistency lasts long enough for practical work. Until independent evaluations and release details appear, Genie 4 is best understood as a demonstrated research and product direction, not a generally available tool with verified performance across the uses described.
Key Questions
What is Google Genie 4?
Genie 4 is a world model that DeepMind says generates scenes frame by frame in response to user controls and text prompts, rather than rendering a finished video or using a stored 3D map.
Can the public use Genie 4 now?
No public release was announced. DeepMind said access would start with trusted testers, with planned availability for Google AI Ultra subscribers through Project Genie and early Gemini API partners. A date was not provided.
How long can a Genie 4 world run?
DeepMind describes “a few minutes” of continuous interaction. TechCrunch and Bloomberg, as cited by heise, reported scenes lasting up to about two minutes. The exact limit has not been clearly stated by DeepMind.
Does Genie 4 train real robots?
The cited Apollo example was a robotics simulation; no physical robot was involved. DeepMind has not established in the supplied material that Genie 4 is being used to train robots in real-world settings.
What are Genie 4’s main limitations?
DeepMind says objects and details can drift over time and describes interactions lasting a few minutes. The company has not published benchmarks that independently verify performance or consistency.
Source: ThorstenMeyerAI.com
