we_are_coded.by CODE · The world, decoded
БГ

Google · Frontier

Genie 4 is now in the Gemini API and AI Studio: 720p worlds at 24fps with synchronized audio and a SynthID watermark

Google announced on 19 November that Genie 4 is available to developers through the Gemini API and Google AI Studio. From a text prompt or a reference image, it generates continuous 720p worlds at 24fps with synchronized audio, and every output carries an imperceptible SynthID watermark.

Source
Google
Published
The event
Checked on
Responsible editor
Cvetelin Ivanov
How we work
MethodCorrections

You press a key and the weather in the world changes. Genie 4 is now available to developers through the Gemini API (via the Interactions API) and Google AI Studio, and from a text prompt, a reference image, or both, it generates continuous 720p worlds at 24fps with synchronized audio. That is how Google announces it.

Fact

The facts: on 19 November 2026 Google announced that Genie 4 is available to developers through the Gemini API (via the Interactions API) and Google AI Studio, a day after the Genie 4 launch. Starting from a text prompt, a reference image, or both, developers can experiment with generating continuous 720p worlds at 24fps with synchronized native audio: from ambient soundscapes and sound effects to character dialogue. Using real-time keyboard controls alongside live text prompts, you can navigate environments and change weather, lighting, objects, or events on the fly. In Google's words, Gemini reasoning keeps the world state consistent and coherent throughout. Every output includes imperceptible SynthID watermarking. Google also says Genie 4 opens up a blank canvas for prototyping interactive experiences, visualizing designs for spatial concepts, and training robotics and AI agents.

The watermark is the quiet part. Every output is marked with an imperceptible SynthID, without the eye catching it. Google says it as a reminder, not as news.

The world is generated while you walk through it.

What it is for. Google lists prototyping interactive experiences, visualizing spatial ideas and training robotics and AI agents. All of that is Google's own wording in the announcement, and the page has no outside check.

Genie 4 launched yesterday, and today we know only what Google writes on this page. The canvas is blank.

The visual is generated code-art, no third-party images.