Gemini Omni 1.1 Flash
Gemini Omni 1.1 Flash is a production-ready generative video model designed to give developers more control over AI video creation and editing. It can extend an existing scene in 10-second increments up to 40 seconds while analyzing as much as 10 seconds of prior context, improving visual consistency and narrative continuity across longer sequences. Developers can specify both the first and last frame of a shot, and the model generates continuous motion between them for smooth transitions, camera orbits, zooms, and seamless looping clips. A 360p preview mode supports faster prototyping and storyboard iteration, while final videos can be generated at 1080p or upscaled to 4K for polished professional production. Omni 1.1 also accepts up to three seconds of reference video as multimodal input, helping preserve visual context, character consistency, motion, and scene direction.
Learn more
Gemini Omni Flash
Gemini Omni is Google’s new model family where Gemini’s ability to reason meets the ability to create, starting with video. The first model in the family, Gemini Omni Flash, can create anything from any input by combining images, audio, video, and text as input, then generating high-quality videos grounded in Gemini’s real-world knowledge. It gives users an easier way to edit video through conversation, where every instruction builds on the last, characters stay consistent, physics hold up, and the scene remembers what came before. Users can transform specific details or entire worlds, reimagine action, add new characters or objects, change environments, adjust camera angles, refine styles, and build multi-turn edits without losing the thread of the original scene. Gemini Omni is designed to bridge photorealism and meaningful storytelling by reasoning about what should happen next, using an intuitive understanding of forces like gravity, kinetic energy, and fluid dynamics.
Learn more
CyberCut
CyberCut is an AI-powered video-editing studio designed to make creating viral, social-ready videos effortless and fast. It turns raw footage or scripts into polished videos using a suite of tools; automatic long-to-short conversion segments long recordings into high-engagement clips; a “Script to Video” mode lets users upload a script or idea and automatically generate a full video, complete with AI voice-overs or digital avatars, ready for publishing; and a text-based editing interface lets creators edit by manipulating transcripts instead of wrestling with traditional video timelines. CyberCut also auto-generates high-precision subtitles (with support for 99+ languages), adds trending effects, soundtracks, and other media assets with one click, and offers material suggestions to optimize engagement and conversion.
Learn more
ChatCut
ChatCut is an AI-powered video editing platform that lets users edit footage using natural language prompts, making complex edits as simple as talking to an assistant. Just upload your video and describe what you want done, and the AI generates polished output. It converts spoken content into transcripts and searchable text, enabling intuitive transcript-based editing, topic- or theme-driven clip grouping, and rapid extraction of highlights, soundbites, or key segments. ChatCut supports web-based editing with contextual AI search to find moments by topic or emotion, drag-and-drop arranging, and timeline fine-tuning, plus XML export for seamless integration with professional tools like Adobe Premiere and DaVinci Resolve. It can remove repeated takes, create social clips, and assemble narratives from raw footage with minimal manual effort, and is expanding toward features like AI-generated motion graphics and music directly in the editor.
Learn more
