Google Genie 4 Now Available in the Gemini API and AI Studio: 720p, 24fps Interactive Worlds with Native Audio
Google announced that Genie 4 is now available to developers through the Gemini API (Interactions API) and Google AI Studio. Developers can generate navigable 720p, 24fps worlds with synchronized audio from text or reference images. Every output carries a SynthID watermark. Pricing and regional availability are not covered in the announcement.
News date: About 5 min read
Contents
Google announced that, following the Genie 4 launch the day before, Genie 4 is now open to developers through the Gemini API and Google AI Studio. An API is the interface that lets programs call Google services; here Genie 4 is accessed via the Interactions API. Google AI Studio is Google's web-based development tool. The announcement does not call it a preview or beta, and it does not list plan tiers or regional restrictions, so please check Google's official documentation for those conditions. For developers, this means they can experiment directly with interactive generated worlds in the API and the web tool. Suggested uses include prototyping, visualizing spatial concepts, and training robots and AI agents (AI programs that can carry out tasks on their own).
What can Genie 4 do in the Gemini API?
According to Google, developers can start from a text prompt, a reference image or a combination of both to experiment with generating continuous worlds at 720p (screen resolution) and 24fps (24 frames per second). The worlds come with synchronized native audio covering ambient soundscapes, sound effects and character dialogue.
Google says users can move through the environment with real-time keyboard controls and real-time text prompts, and swap weather, lighting, objects or events on the fly. Google also says Gemini's reasoning keeps the world state consistent and coherent. World state means what exists in the scene and where it is.
| Aspect | What Google says |
|---|---|
| Availability | Gemini API (via the Interactions API), Google AI Studio |
| Input | Text prompts, reference images, or both |
| Output specs | Continuous worlds, 720p, 24fps |
| Audio | Synchronized native audio (ambient sound, sound effects, character dialogue) |
| Interaction | Real-time keyboard controls and real-time text prompts |
| Watermark | SynthID in every output |
Who will use it, and how does it affect workflows?
Google says Genie 4 can be used to prototype interactive experiences, visualize spatial design concepts, and train robots and AI agents. Google describes it as a "blank canvas" for testing ideas. Google also says developers can try an interactive canvas and starter apps in Google AI Studio.
All of the above is Google's own description of the use cases. The announcement provides no independent test results on actual performance, latency or stability, so readers should evaluate for themselves whether it meets their needs.
What is the SynthID watermark, and what does it mean for users?
Google says every Genie 4 output carries an imperceptible SynthID watermark. According to Google DeepMind, SynthID embeds a digital watermark into AI-generated images, audio, text or video. Humans cannot perceive the watermark, but SynthID technology can detect it.
Google DeepMind says watermarks in images and video are added at the time the content is generated. They are designed to withstand modifications such as cropping, adding filters, changing frame rates or lossy compression (compression that shrinks files by discarding some detail). Users can upload images, video or audio to Gemini, Search and Chrome to check for a SynthID watermark. The SynthID Detector portal is also being opened to everyone. It covers content from Google and partners, including OpenAI, NVIDIA, Kakao, and Apple, which is coming soon.
How do I get started?
Google's announcement only says that you can try an interactive canvas and starter apps in Google AI Studio. It also says to consult pricing and the Gemini API documentation to start building. It gives no specific steps or commands, so please rely on the official documentation.
Frequently asked questions
How is this different from the Genie 4 launch the day before?
The earlier announcement launched Genie 4 itself. This one adds developer access: Google says developers can now use Genie 4 through the Gemini API (via the Interactions API) and Google AI Studio.
Can I try it without writing code?
Google says you can try an interactive canvas and starter apps in Google AI Studio. To integrate it into your own product, consult the Gemini API documentation.
Can the generated content be identified as AI-made?
Google says every output carries a SynthID watermark. Google DeepMind explains that you can upload content to Gemini, Search or Chrome to check whether it contains a SynthID watermark.
What does it cost, and is it available where I live?
The announcement does not provide pricing or regional details. It only points readers to the pricing page and the Gemini API documentation, so please rely on official information.
Browse the latest news in this topic
Found this guide helpful? Share it with someone who needs it
Claude Code 2.1.329: Code Mode Works With Telemetry, /tasks Lists Scheduled Tasks, macOS Computer Use Gets Stricter Safety Rules
Anthropic's changelog lists Claude Code 2.1.329, covering Code Mode behavior changes, new diagnostics in /tasks and /mcp, /code-review changes, and new safety rules for macOS computer use.
Kimi Code CLI v2.7.0 Adds a Native Amazon Bedrock Provider: Use Your AWS Credentials Instead of a Separate API Key
AWS Rounds Up 13 SageMaker Inference Features: Managed NVIDIA Dynamo on HyperPod, MIG GPU Partitioning, Cross-Region Routing
BMW Group Shares How It Governs AI Agents: 12,500+ Developers, Three Autonomy Levels and a Four-Stage CI/CD Gate
Sources
Compiled from the references and verification dates listed above; fares, schedules, product features, and terms can change, so please confirm the latest details on the relevant official website before travelling, booking, or purchasing.