The Information Machine
Updated todayNew2 sources

DeepMind Launches Genie 4 With Native Audio and Real-Time Editing

The gist

Genie 4 is the first version of the model to include native audio and mid-session world editing, expanding what users can do within a single interactive session. The addition of a conversational creation agent lowers the input barrier for building interactive environments.

When stories like this move, I write about them in an email each morning.

One free email each morning, around 8 AM US Eastern.

The full picture

DeepMind has released Genie 4, the latest version of its Project Genie interactive world model, available to Google AI Ultra subscribers. Genie 4 adds real-time native audio that adapts dynamically to scenes, including ambient soundscapes and character dialogue, and allows users to edit generated worlds mid-session using natural-language prompts to change weather, characters, and environments. A new Project Genie agent lets users describe a vision conversationally, with Google's multimodal models building initial visuals and custom background scores. Genie 3 also receives upgrades: extended sessions up to 3 minutes (from 60 seconds), world chaining, 360-degree panorama image grounding, and real-time in-world events. A community gallery enables users to explore, remix, and publish worlds; all outputs carry SynthID watermarking and go through safety screening.

How it developed
18 November 2026

DeepMind releases Genie 4 within Project Genie, adding native audio, real-time editing, and a creation agent.

Sources

Get the daily email

When stories like this move, I write about them in an email each morning.

One free email each morning, around 8 AM US Eastern.

See the latest edition · Privacy