ai-multimodal

Process audio, images, video, and documents with Google Gemini.

27|17|Updated Dec 15, 2025

Search Tags:#image #multimodal #video #audio #generation #gemini #document

One-click install

npx skills add https://github.com/vneseyoungster/ChocoVine --skill ai-multimodal-vneseyoungster

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: ai-multimodal
Source: https://github.com/vneseyoungster/ChocoVine/tree/main/.claude/skills/ai-multimodal
Command: npx skills add https://github.com/vneseyoungster/ChocoVine --skill ai-multimodal-vneseyoungster

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, python-dotenv, Pillow, pypdf, python-docx, docx2pdf, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Provides a unified interface to process audio, images, video, and documents, and to generate multimodal outputs using Google Gemini, enabling end-to-end multimedia workflows.

Core Features & Use Cases

Audio processing (transcription, summaries, TTS)
Image understanding (captioning, object detection, OCR)
Video analysis (scene detection, transcription, Q&A, YouTube support)
Document extraction (PDF tables, forms, charts)
Image generation (text-to-image, editing, composition)
Workflow integration with multiple models and contexts

Quick Start

Load the skill and run a sample workflow, e.g., transcribe audio, analyze an image, or generate an image from a prompt using gemini-2.5-flash or gemini-2.5-flash-image. Ensure GEMINI_API_KEY and optional env vars are configured.