Google Unveils Gemini Omni for Video Editing

Google introduced the new model Gemini Omni at this year's Google I/O, offering an innovative solution for video editing and generation. This tool is now available to all subscribers of Google AI Plus, Pro, and Ultra, as well as on YouTube Shorts. Gemini Omni represents an advancement over the previous model, Nano Banana, and allows for the creation of videos from nearly any input. A key feature of Gemini Omni is the ability to edit videos using natural language. Users can input instructions in simple language to make specific changes or adjustments to their videos.

This feature aims to enhance user-friendliness and make video editing more accessible to less tech-savvy users. The tool enables the combination of various media formats, including images, sounds, videos, and text. This functionality opens up new creative possibilities for content creators looking to enrich their projects with diverse elements. The seamless integration of these formats is expected to significantly reduce production time. Another highlight of Gemini Omni is its ability to transfer scenes and individuals across multiple scenes and settings.

This feature could be particularly interesting for filmmakers and video producers who want to implement complex projects with multiple perspectives and scenes. The technology behind this feature is based on Gemini's comprehensive world understanding, capable of processing contextual information. The first model in the Gemini Omni family is named Gemini Omni Flash. This model is specifically optimized for social media use and offers features geared towards creating short videos. Its availability on YouTube Shorts could significantly increase the tool's reach and usage, as this platform attracts a large number of users.

The introduction of Gemini Omni could also impact the competitive landscape in the video editing sector. With the ability to create videos through simple voice commands, Google may appeal to a broader audience that may not possess the technical skills to use complex video editing software. This could lead to increased usage of Google services in the creative domain. The technology behind Gemini Omni employs advanced algorithms and machine learning to optimize the quality of the generated videos. Google has emphasized that users will benefit from continuous improvements enabled by regular updates and adjustments to the algorithms.

These updates are designed to ensure that users always have access to the latest features and enhancements. The launch of Gemini Omni is part of Google's broader strategy to integrate AI-powered tools across various domains. The development aims to foster user creativity while making powerful technologies more accessible. Google plans to further expand the features of Gemini Omni in the coming months and add additional functionalities. Gemini Omni is already available to all subscribers of Google AI Plus, Pro, and Ultra.

Users can start creating and editing videos immediately by trying out the new features. Google has announced that more models and functionalities will follow in the near future to further expand video editing capabilities. The official announcement of Gemini Omni took place on May 21, 2026, during Google I/O, where the company also showcased other innovative products and services.