This skill enables Claude to interface with Google's Veo 3.x model via the Gemini API to generate professional-grade video content directly from text prompts. It streamlines the creation of short-form content like ads, UGC-style clips, and product demos by automating the generation, polling, and downloading of MP4 files. Key capabilities include stitching multiple 8-second segments into longer videos with consistent styling, utilizing reference images for visual guidance, and maintaining continuity across clips through advanced frame-matching techniques.
주요 기능
01Text-to-video generation via Google Veo 3.x API
02Style consistency management via base-style parameters
03CLI-based workflow for polling, downloading, and local processing
04Automated video stitching for extended runtimes
05Support for reference images to guide visual output
0615 GitHub stars
사용 사례
01Prototyping visual scenes for storyboarding and creative direction
02Generating product demonstrations and visual walkthroughs
03Creating short social media ads or UGC-style marketing clips