Generates, extends, and animates high-quality AI videos directly within Claude Code using the Gemini Veo API.
This skill integrates the powerful Gemini Veo API into your Claude Code environment, enabling a full suite of AI video production capabilities. It allows users to generate videos from text prompts, animate static images, interpolate frames between two images, and extend existing video clips by up to 20 segments. With support for native audio synthesis, multiple aspect ratios, and resolutions up to 4K, this skill streamlines complex AI media workflows through a zero-dependency Python interface that handles asynchronous polling and local file management automatically.
Key Features
01Image-to-video animation and frame interpolation
02Reference image support for consistent style and content guidance
03Video extension to lengthen existing clips seamlessly
04Support for high resolutions (up to 4K) and various aspect ratios
050 GitHub stars
06Text-to-video generation with native audio synthesis
Use Cases
01Extending and refining AI-generated footage for longer storytelling sequences
02Generating short-form social media content and cinematic clips from text descriptions
03Animating UI mockups or concept art into motion demonstrations
