ai-multimodal

Process and generate multimedia content using Google Gemini API
Uses the Gemini API to process and generate multimedia: transcribe and summarize long audio, understand images with OCR and object detection, answer questions over long videos, extract tables and forms from PDFs, and generate or edit images and short videos. Aimed at creators who need to batch-process audio, video and artwork inside an agent workflow.
机器翻译 ·
安装方式
npx skills add majiayu000/claude-skill-registry --skill ai-multimodal