Google Gemini
@GeminiApp
You’re in luck! Users in India can now upload videos (from their camera roll or saved files) and use Gemini Omni to edit and transform them. Give it a try and let us know what you think.
11retweets213likes
View on XGoogle Expands Gemini Omni Video Editing to Users in India
Google expanded access to its Gemini Omni video editing features to users in India, enabling them to upload personal videos for AI-driven transformations. This capability uses Gemini Omni, a multimodal model that allows users to modify existing scenes while maintaining the original video's motion and action.
- Availability
- India
- Input sources
- Camera roll and saved files
- Core model
- Gemini Omni
This regional rollout follows the recent Gemini Omni launch and the introduction of Gemini Omni video composition features that synthesize text and images into clips. By targeting India, Google is scaling its most compute-intensive multimodal features to a massive mobile-first audience, positioning its assistant as a viable alternative to specialized creative tools.
You can now use the Gemini app in India to upload files from your camera roll and apply natural language prompts to transform your footage. The update allows for direct media uploads from local storage, enabling users to remix their own content using the model's video-to-video reasoning capabilities.
Still wondering? A few quick answers below.
Users in India can now access these video editing capabilities through the Gemini app. The rollout allows people in the region to upload videos directly from their camera rolls or saved files to perform AI-driven transformations. This expansion targets one of the world's largest mobile markets with Google's latest multimodal AI technology.
Gemini Omni allows users to edit and transform existing video footage using natural language prompts. Unlike standard text-to-video tools that create clips from scratch, this feature enables video-to-video editing where the AI can modify scenes, swap environments, or add objects while preserving the original motion and action of the uploaded file.
Users can upload videos to the Gemini app by selecting files directly from their device's camera roll or from their saved local files. Once the video is uploaded, the Gemini Omni model processes the visual data, allowing the user to provide instructions on how they want the AI to transform or edit the footage.
