Introducing Gemini Omni: Create Anything from Anything

Meet Gemini Omni: where Gemini’s ability to reason meets the ability to create. Omni is our new model that can create anything from any input — starting with video. With Omni, you can combine images, audio, video and text as input and generate high-quality videos grounded in Gemini’s real-world knowledge. You can also easily edit your videos through conversation.

Whether you’re transforming the world around you, reimagining action, or refining complex details through simple conversation, Gemini Omni understands the physics, culture, and context of your vision.

We’re starting with Gemini Omni Flash, rolling out to the Gemini app, Google Flow, and YouTube Shorts.

Watch the full Google I/O 2026 keynote here: https://youtube.com/live/wYSncx9zLIU?

#GoogleIO

Introducing Gemini Omni: Create Anything from Anything

Google’s major unveiling at I/O 2026 is Gemini Omni, a foundational “world model” built to seamlessly bridge the gap between AI reasoning and advanced media creation. While its ultimate goal is to generate any output format from any input, it is launching with a heavy, groundbreaking focus on cinematic video generation and editing.

Rather than just predicting pixels, Gemini Omni simulates reality by combining an intuitive understanding of physical laws (like gravity and momentum) with deep cultural, historical, and scientific context.

Core Capabilities & Features

Multimodal Blending: You can combine text, images, existing video clips, and audio samples into a single, cohesive video prompt.
Conversational Editing: Beyond generating video from scratch, Omni allows you to edit any clip—whether uploaded from your camera roll or AI-generated—through natural language. Every prompt builds sequentially on the last, maintaining perfect background continuity and character consistency.
AI Digital Avatars: Paid subscribers can record a quick selfie video to capture their likeness and voice, creating a reusable digital avatar to easily place themselves directly into generated videos.
Native Audio Generation: The model generates synchronized, realistic background audio and sound effects natively alongside the video track, matching the action perfectly (such as a marble bouncing down a track).

Technical Details & Deployment

Feature	Details
Initial Video Length	Generates up to 10-second clips at launch (product design choice; longer formats are incoming).
First Model Variant	Gemini Omni Flash is the first lightweight, rapid-tier model rolling out immediately.
Safety & Verification	Every piece of media created or edited by Omni automatically embeds an invisible SynthID watermark to ensure digital transparency.

Where to Access It

The “Videos” Tab: A new dedicated workspace inside the Gemini app home for paid subscribers to generate, remix, and conversational-edit video content.
Google Flow & YouTube Shorts: Fully integrated for creator toolkits. Omni Flash features are arriving for free users on YouTube Shorts and YouTube Create to enhance short-form video creation.
Subscription Tiers: Currently rolling out globally to Google AI Plus, Pro, and Ultra subscribers.
Developer API: Specialized APIs are scheduled to launch in the coming weeks for enterprise clients and third-party software integrations.