Gemini Omni Launched: Google Unveils New AI Video Generator at I/O 2026

Google introduced a new family of generative artificial intelligence models called Gemini Omni during Google I/O 2026, expanding the company’s push into AI-powered video generation and editing.

The announcement was made by Demis Hassabis, who described Gemini Omni as a next-generation AI system designed to generate and edit videos using multiple forms of input, including text, photos, audio and existing video clips. According to Google, the first model in the lineup, Gemini Omni Flash, is scheduled to launch this summer. Google Gemini Intelligence Unveiled; Check If Your Android Phone Meets Extreme Hardware Requirements for On-Device AI Features.

Gemini Omni Launched

Meet Gemini Omni — our new AI model that can create anything from any input, starting with video. 🪄#GoogleIO pic.twitter.com/Mq4Vg27kUo

— Google (@Google) May 19, 2026

What Is Gemini Omni?

Google said Gemini Omni builds on the company’s expertise in “world models” and is designed to eventually support the creation of “any type of output from any kind of input.” The company explained that Gemini Omni Flash can generate AI videos using combinations of text prompts, photos, videos and audio inputs.

A key feature highlighted during the keynote was conversational editing. Users will reportedly be able to modify elements such as characters, backgrounds and scenes using natural voice commands. Anthropic Expands Claude AI Integration to Microsoft 365 for All Users.

According to Hassabis, the long-term ambition for the Omni project is to “generate any type of output from any kind of input.” Google also said the system is being positioned as the video-generation counterpart to its Nano Banana image generation model.

Google Positions Omni Flash as Video AI Tool

In a blog post, Google said Omni Flash represents the beginning of a broader AI initiative aimed at multimodal content creation. The company stated that the model can already work across multiple media formats and may eventually evolve into a platform capable of “create anything from any input.”

Google noted that users could, for example, ask the AI tool to insert their likeness into generated videos. Speaking to The Verge, Nicole Brichtova, who leads the product team working on Omni, said the company had observed strong engagement from users creating personalised AI-generated content through earlier image-generation systems.

Built on Google’s Expanding AI Ecosystem

The launch of Gemini Omni comes as Google continues expanding its artificial intelligence portfolio across consumer apps, enterprise tools and creative platforms.

During the keynote, the company also referenced the popularity of its Nano Banana image generation system, which Google said has been used to create more than 50 billion AI-generated images since its launch last year.

The announcement reflects increasing competition among major technology firms developing generative AI tools capable of producing video, audio and interactive content from simple prompts.

The unveiling of Gemini Omni adds Google to the growing list of companies investing heavily in AI-generated video technology.

Technology firms have increasingly focused on multimodal AI systems capable of processing and generating content across different formats, including text, images, sound and video.

While companies have promoted such tools for creative and productivity use cases, the rapid growth of AI-generated media has also raised broader discussions around authenticity, copyright, deepfakes and responsible AI deployment. Google has not yet announced detailed public rollout timelines beyond confirming that Gemini Omni Flash is expected to launch this summer.

(The above story first appeared on LatestLY on May 19, 2026 11:27 PM IST. For more news and updates on politics, world, sports, entertainment and lifestyle, log on to our website latestly.com).