Generates high-quality AI videos and animations using Google Veo models via the AceDataCloud API.
The veo-video skill integrates Google’s powerful Veo video generation models into the Claude Code environment, allowing users to create cinematic videos from text prompts or animate still images. It supports the latest Veo 3 and 3.1 iterations, which feature native audio generation, as well as specialized workflows for upscaling content to 1080p and auto-translating prompts. This skill is ideal for developers and creators who need to programmatically generate or enhance video content with fine-grained control over aspect ratios and model performance.
Key Features
015 GitHub stars
02Image-to-video animation to bring static visuals to life with motion
03High-resolution upscaling to convert generated videos to 1080p
04Native audio generation included with Veo 3 and 3.1 models
05Asynchronous task polling for efficient handling of generation workflows
06Text-to-video generation with support for Veo 2, 3, and 3.1 models
Use Cases
01Prototyping visual concepts or storyboards directly from text descriptions
02Enhancing existing image assets by converting them into dynamic video loops
03Automating the creation of marketing clips and social media video content
