Gemini Omni breaks the barrier between text, audio, and video. Generate and edit media using natural language commands.
You no longer need complex timeline editors to make quick adjustments. Speak or type to Gemini Omni, and it will trim, add sound effects, generate B-roll, and composite your video in real-time.
Take this raw footage. Trim out all the silences, add a subtle lo-fi background track, and generate an engaging animated caption track.
Simply say 'Make the sky darker and add a slow zoom' and Omni processes the raw video file and applies the effects natively.
Omni listens to your voice tone and matches generated background music and sound effects automatically to the mood of the video.
Your new conversational editing suite.
A lightweight visual timeline that updates dynamically as the AI makes edits to your media.
The core input area where you can combine text commands, audio recordings, and reference images.
A responsive video player that renders your AI-driven edits on the fly without waiting for a full export.