--- title: Google’s Genie 4 world model adds audio, more realistic... description: Google DeepMind released Genie 4, a world model that generates photorealistic, interactive simulations with real-time audio. Users can type prompts... canonical: https://daily.dev/posts/google-s-genie-4-world-model-adds-audio-more-realistic-worlds-and-real-time-steering-byu7bdijt twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering | daily.dev og:description: Google DeepMind released Genie 4, a world model that generates photorealistic, interactive simulations with real-time audio. Users can type prompts... og:url: https://daily.dev/posts/google-s-genie-4-world-model-adds-audio-more-realistic-worlds-and-real-time-steering-byu7bdijt og:image: https://api.daily.dev/og/posts/byu7BDijt.png og:image:alt: Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering **[TechCrunch](https://daily.dev/sources/tc)** · 4 min read · 0 upvotes · 0 comments ## Summary Google DeepMind released Genie 4, a world model that generates photorealistic, interactive simulations with real-time audio. Users can type prompts mid-simulation to change the scene, weather, camera angle, or add new objects and people. It holds a consistent scene for up to two minutes, double its predecessor Genie 3's limit, with better physics and more human-like characters. Gemini acts as a director planning steps while Genie renders visuals, including a robotics experiment where a Gemini 4 Argon model broke tasks into steps for Genie to simulate. The team says details can still drift over longer simulations and audio or in-world text accuracy isn't solved yet. Genie 4 is available now as a research preview for trusted testers, with wider rollout to Google AI Ultra subscribers and API partners coming. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What new features does Google's Genie 4 world model have compared to Genie 3? Genie 4 adds real-time audio including music, ambient noise, and dialogue, plus freeform mid-simulation edits like changing weather, camera angle, or adding objects and people. It maintains a consistent scene for up to two minutes, double Genie 3's limit, with improved physics and more human-like characters. It is available as a research preview for trusted testers. _Developers tracking generative world models can follow Genie 4's rollout and capabilities on daily.dev._ ### Is Google's Genie 4 world model publicly available? No, Genie 4 is currently available only as a research preview for trusted testers. Google plans to roll it out in the coming weeks to Google AI Ultra subscribers through Project Genie, and to early access partners of the Gemini API and Google AI Studio. _Those evaluating access to new generative AI tools can watch the rollout timeline on daily.dev._ ### How does Gemini work together with Genie 4 in Google's hybrid world model approach? Gemini acts as a director that plans steps and checks frames while Genie 4 generates the visuals. In a research experiment tied to Gemini Robotics, a Gemini 4 Argon model broke tasks into steps that Genie 4 simulated in real time, testing a way to rehearse robot scenarios in simulation before real-world deployment. _Engineers combining LLM planning with generative simulation can track this hybrid approach on daily.dev._ ## Similar posts on daily.dev - [Google's Genie 3 world models start to break down after around a minute](https://daily.dev/posts/google-s-genie-3-world-models-start-to-break-down-after-around-a-minute-8opcxsmvb) · GamesIndustry.biz · 2 upvotes · 0 comments - [Google DeepMind connects Street View to Project Genie world model](https://daily.dev/posts/google-deepmind-connects-street-view-to-project-genie-world-model-uak71o9wk) · The Next Web · 1 upvotes · 0 comments - [World Models: The Quiet Race to Build AI That Understands Reality, Not Just Language](https://daily.dev/posts/world-models-the-quiet-race-to-build-ai-that-understands-reality-not-just-language-2pfjhmqhl) · Medium · 0 upvotes · 0 comments --- Tags: [#genai](https://daily.dev/tags/genai), [#google-gemini](https://daily.dev/tags/google-gemini), [#google-deepmind](https://daily.dev/tags/google-deepmind), [#world-models](https://daily.dev/tags/world-models) [View this post on daily.dev](https://daily.dev/posts/google-s-genie-4-world-model-adds-audio-more-realistic-worlds-and-real-time-steering-byu7bdijt) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering","url":"https://daily.dev/posts/google-s-genie-4-world-model-adds-audio-more-realistic-worlds-and-real-time-steering-byu7bdijt","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/google-s-genie-4-world-model-adds-audio-more-realistic-worlds-and-real-time-steering-byu7bdijt"},"datePublished":"2026-10-27T16:32:07.884Z","dateModified":"2026-10-27T17:06:26.991Z","description":"Google DeepMind released Genie 4, a world model that generates photorealistic, interactive simulations with real-time audio. Users can type prompts...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b46d2be38354fc4f88a4898e93069fd9?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b46d2be38354fc4f88a4898e93069fd9?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"TechCrunch","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"TechCrunch","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/tc","url":"https://daily.dev/sources/tc"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/google-s-genie-4-world-model-adds-audio-more-realistic-worlds-and-real-time-steering-byu7bdijt","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"genai,google-gemini,google-deepmind,world-models","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"TechCrunch","item":"https://daily.dev/sources/tc"},{"@type":"ListItem","position":3,"name":"Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/google-s-genie-4-world-model-adds-audio-more-realistic-worlds-and-real-time-steering-byu7bdijt#faq","mainEntity":[{"@type":"Question","name":"What new features does Google's Genie 4 world model have compared to Genie 3?","acceptedAnswer":{"@type":"Answer","text":"Genie 4 adds real-time audio including music, ambient noise, and dialogue, plus freeform mid-simulation edits like changing weather, camera angle, or adding objects and people. It maintains a consistent scene for up to two minutes, double Genie 3's limit, with improved physics and more human-like characters. It is available as a research preview for trusted testers. Developers tracking generative world models can follow Genie 4's rollout and capabilities on daily.dev."}},{"@type":"Question","name":"Is Google's Genie 4 world model publicly available?","acceptedAnswer":{"@type":"Answer","text":"No, Genie 4 is currently available only as a research preview for trusted testers. Google plans to roll it out in the coming weeks to Google AI Ultra subscribers through Project Genie, and to early access partners of the Gemini API and Google AI Studio. Those evaluating access to new generative AI tools can watch the rollout timeline on daily.dev."}},{"@type":"Question","name":"How does Gemini work together with Genie 4 in Google's hybrid world model approach?","acceptedAnswer":{"@type":"Answer","text":"Gemini acts as a director that plans steps and checks frames while Genie 4 generates the visuals. In a research experiment tied to Gemini Robotics, a Gemini 4 Argon model broke tasks into steps that Genie 4 simulated in real time, testing a way to rehearse robot scenarios in simulation before real-world deployment. Engineers combining LLM planning with generative simulation can track this hybrid approach on daily.dev."}}]} ```