skills.rest
zircote
zircoteCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ai-multimodal

Process audio, image, video, and documents via Gemini's multimodal API.

3|Updated Jan 17, 2026
Search Tags:#image#ai#multimodal#video#audio#gemini#document
One-click install
npx skills add https://github.com/zircote/agents --skill ai-multimodal-zircote
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-multimodal
Source: https://github.com/zircote/agents/tree/main/skills/ai-multimodal
Command: npx skills add https://github.com/zircote/agents --skill ai-multimodal-zircote

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Processing multimedia content across audio, images, video, and documents is fragmented across multiple tools. This Skill orchestrates Gemini's multimodal API to deliver unified insights and generation in a single workflow.

Core Features & Use Cases

  • Transcribe audio with timestamps and speaker labels.
  • Caption and describe images, perform OCR, and extract structured data from documents.
  • Analyze videos for scene changes, key moments, and YouTube content; generate outputs in JSON or Markdown.
  • Generate new media such as images or enhanced outputs from prompts, all within a single interface.
  • Use cases include media analysis for content creation, research, and QA automation.

Quick Start

Provide media files or references along with a concise prompt to Gemini's multimodal API to obtain structured results.

Frequently Asked Questions about ai-multimodal

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe audio and extract text from images using a single Gemini workflow?▼

Transcribe audio and extract text from images using Gemini's multimodal API to process inline data or File API uploads, returning unified insights like speaker labels and OCR results in JSON or Markdown.

Can I analyze video for scene changes and generate JSON outputs with Gemini?▼

Analyze video for scene changes and key moments using Gemini's multimodal API, which processes video content to detect transitions and produces structured outputs in JSON or Markdown formats.

Do I need python-docx and pypdf to process documents with this multimodal AI approach?▼

Yes, processing documents requires dependencies like pypdf and python-docx to extract structured data, alongside the google-genai package to handle the multimodal API interactions.

What is the best way to generate images and perform OCR on documents without switching tools?▼

Generate images and perform OCR on documents using a unified multimodal API interface, which orchestrates media handling and model selection to deliver generation and extraction within a single workflow.

Does Gemini multimodal processing support YouTube video content and inline data uploads?▼

Gemini multimodal processing supports analyzing YouTube content and handling both inline data and File API uploads, enabling scene detection and Q&A across various media types.

Why does multimodal media processing fail when dependencies are missing?▼

Multimodal media processing fails without required dependencies because the workflow relies on libraries like pillow for images, pypdf for documents, and google-genai for robust API error handling.

Related Skills

Explore More Software Engineering Skills→
locdinh209locdinh209

ai-multimodal

Process and generate multimedia content using the Google Gemini API.

Community
Advanced
carterwayneskhizeinecarterwayneskhizeine
19

ocr-and-documents

Extract text and structured content from PDFs and scanned documents.

Community
Intermediate
AbdullahMalik17AbdullahMalik17
9

docx

Create, edit, and analyze Word documents with tracked changes and comments.

Community
Advanced
felix-howardfelix-howard

ck:ai-multimodal

Analyze images, audio, and video and generate media via Google Gemini.

Community
Advanced