🔍 Read the full analysis: Who Gets To Use Google’s Genie 4? A Guide To Its AI Worlds 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 demonstrated Genie 4 on October 27, describing it as a real-time AI world model that responds to movement and text prompts while generating visuals and audio. Access is limited to trusted testers for now; Google says broader availability is planned for Google AI Ultra subscribers through Project Genie and early Gemini API partners, but has not given a date or API price.
Google DeepMind demonstrated Genie 4 on October 27, a real-time AI system that generates interactive scenes in response to user movement and text instructions. The company says it will first be available to trusted testers, with access planned later for Google AI Ultra subscribers through Project Genie and early Gemini API partners; it has not announced a release date or API price.
DeepMind describes Genie 4 as a world model: rather than rendering a completed video or drawing a scene from a stored 3D map, it generates what happens next as a person moves through the environment or gives instructions. In the company’s demonstrations, users steer scenes with keyboard and mouse controls and can type changes such as adjusting the weather. DeepMind says the system can generate visuals and sound together, including environmental audio, music and character dialogue.
The company also says Gemini 3.8 Flash can monitor the scene, break a goal into steps and help guide what the model generates. DeepMind’s examples include more realistic people and simulated physics, as well as a robotics research demonstration involving a simulated Apptronik Apollo humanoid playing checkers. That example was a simulation; the source reports that no real robot was involved.
For now, the demonstrations are company-selected examples, not an open product test. DeepMind has not published benchmark figures in the supplied announcement material. The company acknowledges that objects and details can shift or drift over time and says Genie 4 supports only a few minutes of continuous interaction. TechCrunch and Bloomberg, as cited by heise, reportedly describe scenes lasting about two minutes; that figure does not appear in DeepMind’s own description.
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
Who Gets Access to Genie 4
The announced access plan puts Genie 4 outside general public use for now. DeepMind says trusted testers are using it, with Google AI Ultra subscribers expected to get access through Project Genie and early Gemini API partners also slated to try it. The source identifies Google AI Ultra as a $200-a-month tier, but DeepMind has not confirmed a Genie-specific charge, an API price or when either route will open.
That distinction matters because the polished demonstrations do not establish that the system is ready for ordinary users or dependable commercial work. Feedback about film previsualization and game prototypes is reported as tester experience, not as a broadly available service or independently measured performance. For companies, the announcement is an indication of possible creative and simulation uses, while access, reliability and cost remain unsettled.
Genie 4’s ability to produce sound with generated scenes also raises questions about how synthetic media may be recognized. DeepMind says every Genie 4 video and audio output carries an invisible SynthID watermark. That is the company’s stated safeguard; the announcement does not provide details about how the watermark performs in practice or how users will check for it.
Popular right now
Bose QuietComfort Wireless Bluetooth Headphones with Active Noise Cancellation, Mic, USB‑C Charging, Deep Bass, 24‑Hour Battery – White Smok
Apple AirPods Pro 3 Wireless Earbuds with Active Noise Cancellation
Bose QuietComfort Wireless Noise-Cancelling Over-Ear Headphones, Black
As an affiliate, we earn on qualifying purchases.
From Genie 3 to Genie 4
The announcement follows a sequence of increasingly interactive systems. The first Genie, introduced in February 2024, generated simple 2D worlds and was described in its research paper as an 11-billion-parameter model trained on unlabeled internet videos. Genie 2, announced in December 2024, generated 3D worlds from a single image and could maintain them for up to a minute, although its real-time version was a reduced-quality system.
In August 2025, DeepMind introduced Genie 3 as its first real-time world model. The company described it as running at 720p and 24 frames per second, with worlds remaining consistent for a few minutes and visual memory extending about a minute into the past. Google opened Genie 3 through Project Genie to paying U.S. subscribers in January 2026. TechCrunch reported a 60-second limit per world at that time and linked the limit partly to computing costs.
DeepMind presents Genie 4 as a step toward more realistic, responsive worlds, with native audio generation and live text changes among the additions. Its demonstrations and descriptions are company material, so they show what Google says the system can do, not a third-party evaluation of its performance.
“Objects and details can shift or drift over time.”
— Google DeepMind
Release Timing and Reliability
No public launch date has been announced for Project Genie access, and there is no stated price for Gemini API use. The source does not clarify which testers qualify, which countries will be included, or what limits subscribers and partners will face. DeepMind’s phrase “coming soon” does not specify a timetable.
Performance also remains difficult to judge from the available material. DeepMind has not supplied benchmark numbers, and its selected clips do not establish how consistently Genie 4 handles longer sessions, complex instructions or repeated movement through a scene. The company itself warns that details may drift. The reported roughly two-minute scene duration comes from media reports, not from DeepMind’s own published wording.
Potential uses should be treated with similar care. Film and game development examples are described as tester feedback, while the humanoid-robot example is a research simulation. The supplied information does not establish that Genie 4 is ready to train physical robots or to support production workflows.
The Next Access Milestones
The next concrete development will be the start of access for Google AI Ultra subscribers and early Gemini API partners, which DeepMind says is planned but has not dated. Google has not specified whether access will open to all subscribers at once, how much usage will be permitted, or when an API price will be published.
Further evidence will depend on access beyond company-selected demonstrations: independent testing, published performance measures and more detail about scene length and consistency would help clarify what Genie 4 can reliably support. Until then, its stated capabilities and limitations should be understood as DeepMind’s account of a system still limited to testing, rather than a generally available tool.
Key Questions
Can the public use Genie 4 now?
No. The supplied report says Genie 4 is currently limited to trusted testers. DeepMind has described later access for Google AI Ultra subscribers through Project Genie and early Gemini API partners, but has not announced a public release date.
How much will Genie 4 cost?
No Genie 4 price has been announced. The source identifies Google AI Ultra as a $200-a-month subscription tier, but does not say whether access will involve any additional charge. The Gemini API price is also unknown.
What does Genie 4 do?
DeepMind says Genie 4 generates interactive scenes as users move and type instructions, with sound generated alongside the visuals. The company also describes Gemini 3.8 Flash as helping guide and monitor the generated scene.
Can Genie 4 train real robots?
The source describes a robotics research demonstration in which a humanoid was simulated playing checkers. No physical robot was involved in that example, and the available information does not establish that Genie 4 is ready to train real robots.
How long can a Genie 4 world last?
DeepMind says the system supports a few minutes of continuous interaction and warns that details can drift. TechCrunch and Bloomberg, as cited by heise, report scenes of about two minutes, but that specific duration is not in DeepMind’s own description.
Source: ThorstenMeyerAI.com
