Google Expands Gemini Omni AI Video Editing Tool to India

​Google has expanded the availability of its AI-powered video creation and editing tool, Gemini Omni, to users in India. The tool allows users to edit videos by describing desired changes in natural language. This development follows the initial introduction of Gemini Omni at Google's I/O developer conference earlier this year.

Key Highlights

• Google launches Gemini Omni AI video editing tool in India.
• Users can edit videos using natural language prompts through Gemini app and web.
• Gemini Omni supports multimodal input including text, images, video, and voice.
• Videos generated are limited to 10 seconds with audio and include SynthID watermark.
• Feature available to Google AI Plus, Pro, and Ultra subscribers globally.

Gemini Omni Features and Capabilities

​Gemini Omni is Google's flagship multimodal AI model. It can understand and generate content across text, images, audio, and video. The model combines Gemini's reasoning abilities with advanced content creation tools. Users can upload videos directly to Gemini Omni and edit them using simple text prompts. This feature is now available through the Gemini app and Gemini's web platform.

The first model in the Gemini Omni lineup, called Gemini Omni Flash, is rolling out across the Gemini app, Google Flow, and YouTube Shorts. Google plans to make the technology available to developers and businesses through APIs in the coming weeks.

Gemini Omni supports multiple forms of input, including text, images, videos, and voice references. This allows users to generate new video content or edit existing clips by combining different types of prompts. The model can interpret and act on these prompts to add visual effects, change scene styles, modify objects, or alter the overall look of a video.

Editing Process and User Experience

To use Gemini Omni, users need to open the Gemini app or visit gemini.google.com. After uploading a video clip, users describe the changes they want using text prompts. The system supports conversational editing, enabling users to refine videos through follow-up instructions. This process resembles interacting with an AI assistant.

Gemini Omni remembers previous edits and builds on them over multiple prompts. It maintains consistency in scenes, characters, and objects. Users can gradually adjust a video until they achieve the desired result, without restarting the editing process each time.

Google has also introduced a feature called Avatars. This allows users to create videos featuring a digital version of themselves, using their own voice. Every video generated with Gemini Omni includes Google's SynthID digital watermark, helping to identify AI-generated content. Users can verify whether a video was created with AI through Gemini, Gemini in Chrome, and Google Search.

Limitations and Availability

Currently, Gemini Omni can generate video clips of up to 10 seconds with audio. Google is working to extend this limit in the future. The rollout of Gemini Omni Flash is global, including India. It is available to Google AI Plus, Pro, and Ultra subscribers through the Gemini app and Google Flow. The technology is also being integrated into YouTube Shorts and the YouTube Create app, making it accessible to a wider audience.