The whole dayWed 18 Nov 2026
AI Compass
WeeklyArchiveAbout

Google DeepMind rolls out Genie 4 with live audio in Project Genie

Available on 18 November 2026 in the browser for eligible Google AI Ultra subscribers with Pro waitlist sign-ups, conversational world building and remixing.

Video: Google DeepMind · YouTube

Google DeepMind and Google Labs began rolling out Genie 4 inside the browser-based Project Genie platform on 18 November 2026 for eligible Google AI Ultra subscribers, while opening a waitlist for Google AI Pro members. Unlike earlier static prompt-to-world prototypes, Genie 4 lets users type natural-language prompts mid-session while navigating an interactive 3D space to change weather, spawn characters or redirect events on the fly, paired for the first time with adaptive real-time native audio spanning ambient soundscapes and character dialogue.

Conversational Project Genie agent, community gallery and Genie 3 upgrades

A new conversational Project Genie agent coordinates Google’s multimodal and Gemini models to establish a world’s visual look and custom mood-matched background score from plain dialogue. During live exploration, Gemini watches the screen to surface context-aware suggestion chips or trigger in-world events automatically, complementing physical-simulation work such as Google DeepMind’s Gemini 4 Hydrogen robotics plugin.

Creators can publish and remix interactive worlds in a new community gallery seeded with collaborations including creative technologist Will’s gothic mystery Villa Giallo and filmmaker Anand Gandhi’s colony simulation The Life of Ants. Alongside Genie 4, Google kept an upgraded Genie 3 in Project Genie’s model picker for 3-minute runs (up from 60 seconds), multi-world chaining and 360-degree panorama grounding. Google DeepMind has not announced standalone API access for Genie 4.

Technical details

Access tier and surface
Browser-based Project Genie for eligible Google AI Ultra subscribers; waitlist open for Google AI Pro
Genie 4 interactive additions
Real-time mid-session text editing, adaptive native audio and dialogue, plus conversational Project Genie agent
Genie 3 picker upgrades
3-minute generations (up from 60 seconds), multi-world chaining and 360-degree panorama grounding
Featured gallery worlds
Villa Giallo, The Life of Ants, Living Memory, Dino Field Guide and Gemini-refereed Rock Paper Scissors

Release details & context

When to pick Genie 4 versus upgraded Genie 3 inside Project Genie

Inside Project Genie’s model selector, Google positions Genie 4 for maximum visual realism, responsive physics and real-time native audio, while retaining Genie 3 for creators who want longer continuous 3-minute traversals, linked multi-biome world journeys across forests, underwater ruins and icy seas, or scenes anchored to uploaded 360-degree panoramas such as Petra’s canyon facade.

Curated gallery templates demonstrate distinct Gemini-in-the-loop mechanics, including transforming personal photographs into walkable Living Memory scenes and running tabletop Rock Paper Scissors matches where Gemini acts as a live visual referee.

Common questions

Who can access Genie 4 inside Project Genie at launch?

Genie 4 is rolling out in the browser to eligible Google AI Ultra subscribers, while Google AI Pro members can join a waitlist on the Project Genie site.

Why does Project Genie still include Genie 3 alongside Genie 4?

Upgraded Genie 3 supports extended 3-minute sessions, linked world chaining and 360-degree panorama image grounding when longer runs take priority over Genie 4’s native audio and higher fidelity.

Google DeepMind release timeline (11 launches tracked)

  1. Earlier10 Nov 2026
    Google DeepMind unveils Gemini Robotics 2.5 for dexterous manipulation and factory kitting

    Google DeepMind rolls out Gemini Robotics 2.5, reaching 96% autonomous kitting accuracy on Apollo 2 humanoids in Mercedes-Benz factory pilots.

  2. Earlier11 Nov 2026
    Google DeepMind releases AlphaGenome 2 API for single-cell DNA variant prediction

    Google DeepMind launches AlphaGenome 2 with custom scRNA-seq conditioning, imputed tracks and CpG methylation scoring across 1 Mb DNA windows.

  3. Earlier13 Nov 2026
    Google DeepMind opens PARDIG and SatWeave datasets from WeatherNext 3

    Google DeepMind releases the PARDIG 15-minute precipitation and SatWeave 5-satellite mosaic datasets powering WeatherNext 3 on Google Cloud.

  4. Earlier17 Nov 2026
    Google DeepMind launches Gemini 4 Hydrogen robotics plugin for Antigravity

    Google DeepMind ships a Robotics plugin for Google Antigravity powered by Gemini 4 Hydrogen for 10-minute USB arm setup and MuJoCo sim-to-real control.

Explore the full Google DeepMind dossier or browse all model releases.

Also in the Wednesday 18 November edition

Read all 18 launches on one page
  1. 01
  2. 03
  3. 04
  4. 05
  5. 06
  6. 07
  7. 08
  8. 09
  9. 10
  10. 11
  11. 12
  12. 13
  13. 14
  14. 15
  15. 16
  16. 17
  17. 18

Spotted an error? Email aiforsuccess.in+compass@gmail.com or tag @ai_for_success on X