Google just opened Genie 4 to developers, and the part I keep coming back to is the sound.
The world model is now in the Gemini API and Google AI Studio. Start with a text prompt, a reference image, or both, and it generates a continuous 720p world at 24 frames per second, with synchronized native audio: ambient soundscapes, sound effects, and character dialogue. You steer it in real time with the keyboard and live text prompts, changing weather, lighting, objects, or events on the fly. Gemini's reasoning is meant to keep the world consistent as you go.
What I find interesting is what that does to game audio. The world doesn't just look playable. It arrives with its own sound already in sync.
If every generated world can come with ambient audio, effects, and dialogue built in, what does that mean for game audio, sound design, and composers?
https://blog.google/innovation-and-ai/technology/developers-tools/genie-4-in-gemini-api/
Terminus needs JavaScript to show replies and pictures.