Get App
Download App Scanner
Scan to Download
Advertisement

Google Unveils Genie 4, An AI That Builds Interactive Worlds With Sound On The Spot

Google’s new Genie 4 model can generate interactive, realistic worlds in real time, complete with music, ambient sound and talking characters.

Google Unveils Genie 4, An AI That Builds Interactive Worlds With Sound On The Spot
Google

Google's CEO Sundar Pichai officially introduced the Genie 4, describing it as their "most realistic and interactive world model" while explaining the features. The model is now a research preview for trusted testers.

Sound And Real-Time Controls

Unlike earlier versions, Genie 4 makes sound along with visuals. Music, background noise such as wind or waves, and even spoken dialogue are created together with the world. Characters can talk and react to what the user does in real time.

Also Read | Layoffs Are Rising In Tech, But These Skills Are Helping People Unlock Better Pay

Users move around and control the camera with standard keyboard keys. Typed prompts can change the scene, such as switching the weather, adding a person or an object, or moving the camera. Google's Gemini models adapt these prompts to fit the scene and keep the world consistent as it grows.

ALSO READ | From Farmers To Small Businesses: Google Expands Its AI Push In India

Bigger Leap In Realism

Google says realism is the biggest improvement. Genie 4 simulates physics such as aerodynamics and collisions. Human characters move more naturally and respond to their surroundings. In demos, the model produced a misty lake with a saxophone player, a 1980s Japanese train station and a stained-glass landscape.

Working With Gemini On Multi-Step Tasks

The model also works with Gemini to handle tasks that need many steps. Gemini splits a goal into steps and checks each frame to see if a step worked. It changes the plan if the world changes. Google showed this with robots, including a humanoid playing checkers.

The company sees this as a way to test how AI systems and robots behave in different settings before they face the real world.

Early Testers Put It To Use

Filmmakers are using Genie 4 as a quick draft mode to run scenes and adjust angles, lighting and dialogue. Photojournalists are turning a single archival photograph into a scene that can be explored. Game developers use it to prototype ideas without writing engine code. Some companies are testing it to generate scenarios.

ALSO READ | Google's Gemini 4 Argon Is Here: Sundar Pichai Announces Global Rollout

Still Early Research

Google says this is early research. Details and objects can shift or drift over time, mainly in long sessions or after many edits. Complex physics, accurate audio, readable text and long-term consistency are still being worked on.

Safety And Availability

Google says Genie 4 has strict guardrails and went through internal checks. Every video and audio clip it makes carries SynthID, Google's invisible watermark for AI-generated content.

Genie 4 is coming soon to Google AI Ultra subscribers through Project Genie. It will also reach early-access partners in the Gemini API and Google AI Studio. A waitlist is open.

ALSO READ | Hyperscalers Turn Rivals? Anthropic Flags Critical AI Compute Risk By Google, AWS, Microsoft

Essential Business Intelligence, Sharp Market Insights, Practical Personal Finance Advice, Daily Fuel, Gold and Silver Prices and Latest Stories — On NDTV Profit.

Newsletters

Update Email
to get newsletters straight to your inbox
⚠️ Add your Email ID to receive Newsletters
Note: You will be signed up automatically after adding email

News for You

Set as Trusted Source
on Google Search
Add NDTV Profit As Google Preferred Source
Listen to the latest songs, only on JioSaavn.com