Hermes Vector

AI & SI

Google DeepMind releases Genie 4 to Google AI Ultra subscribers

Google DeepMind has made Genie 4 available to eligible Google AI Ultra subscribers as part of an updated Project Genie experience, alongside new Genie 3 features and a community gallery.

By Hermes Vector

Also in: Español · Português · Français · Deutsch

Checked against 1 sourceGoogle
Illustration for: Google DeepMind releases Genie 4 to Google AI Ultra subscribers

In brief

  • Genie 4 is available to eligible Google AI Ultra subscribers starting November 18, 2026.
  • Genie 4 allows mid-session prompts to change worlds and adds real-time native audio.
  • Genie 3 sessions are extended to up to 3 minutes per generation, up from 60 seconds.
  • All Project Genie video and audio includes SynthID watermarking and safety screenings.

Google DeepMind releases Genie 4 to Google AI Ultra subscribers

Google DeepMind has released Genie 4 to eligible Google AI Ultra subscribers as part of a new Project Genie experience. The announcement was made on November 18, 2026, in a blog post by Diego Rivas, Group Product Manager at Google DeepMind, and Pavan Kumar, Group Product Manager at Google Labs.

Genie 4 capabilities

Genie 4 is described by Google DeepMind as its most realistic and interactive world model yet. Users can prompt mid-session to change the world they created by typing a new prompt while navigating. This allows them to shift the weather, drop in a character, or redirect the action. For the first time, Genie 4 pairs visuals with real-time native audio that adapts as the scene unfolds, from ambient soundscapes to character dialogue.

Genie 3 updates

Genie 3 remains available in Project Genie’s model picker for users who want longer runs or panorama-seeded spaces. Today’s Genie 3 updates include extended sessions and world chaining, allowing users to explore for up to 3 minutes per generation, up from 60 seconds, or link multiple worlds together for longer journeys. Genie 3 also adds 360-degree panorama image grounding to seed new worlds from 360-degree panorama images, and real-time in-world events that let users dynamically change the environment with natural-language prompts while exploring.

Project Genie agent and gallery

The new Project Genie agent helps users build their vision by orchestrating Google’s suite of multimodal models to craft initial visuals establishing a world’s signature look, paired with custom background scores tailored to the mood. Users can bring Gemini models into the session as they explore; the models observe what is happening on screen, surface context-aware suggestion chips for where to go next, or trigger in-world events automatically as the journey unfolds.

The new Project Genie gallery brings together curated worlds and creative work from the community. Examples include “Villa Giallo,” created with Will aka BLVCKL!GHT, which uses Genie 4 to turn a gothic manor into an interactive, room-by-room mystery, and “The Life of Ants,” built with filmmaker Anand Gandhi, which uses Genie 4’s photorealism to let users navigate a colony from an ant’s perspective.

Availability and safety

Eligible Google AI Ultra subscribers can try the new Project Genie experience starting November 18, 2026. Google AI Pro members can join the waitlist on the same page. All video and audio generated in Project Genie includes SynthID watermarking, and all model inputs and outputs go through safety screenings. Google DeepMind says Genie 3 and Genie 4 remain world models in the frontier research space, and that it is actively tackling key challenges such as camera latency, intricate physical interactions, real-time audio precision, and long-term scene permanence.


Sources

This article was drafted with AI assistance and checked against the sources above. Company claims are reported as claims. Cover image is AI-generated.

Questions readers ask

Who released Genie 4 and when was the announcement made?
Google DeepMind released Genie 4 to eligible Google AI Ultra subscribers, with the announcement made on November 18, 2026, in a blog post by Diego Rivas and Pavan Kumar.
What are the new capabilities of Genie 4?
Genie 4 pairs visuals with real-time native audio that adapts as the scene unfolds and allows users to prompt mid-session to change the world by typing new prompts while navigating.
What updates were added to Genie 3?
Genie 3 updates include extended sessions allowing users to explore for up to 3 minutes per generation, world chaining to link multiple worlds, and 360-degree panorama image grounding.
What examples are included in the new Project Genie gallery?
The gallery includes 'Villa Giallo,' created with Will aka BLVCKL!GHT, and 'The Life of Ants,' built with filmmaker Anand Gandhi.
How can Google AI Pro members access Project Genie?
Google AI Pro members can join the waitlist on the same page where eligible Google AI Ultra subscribers can try the new experience starting November 18, 2026.

The day's checked news, by email

One short email a day with the top stories. Free, and you can unsubscribe in one click.

Or follow for the latest news:

How do you feel about this story?

Comments 0

No comments yet. Start the discussion.