skills.rest
Stonelukas
StonelukasCOMMUNITY
Explore all skills by this author →
GitHub

ai-multimodal

Analyze images, audio, and video via Gemini's multimodal API for captions and transcripts.

Updated Jun 16, 2025
Search Tags:#ocr#multimodal#vision#gemini#analyze#transcribe
One-click install
npx skills add https://github.com/Stonelukas/Mouse-on-Numpad --skill ai-multimodal-stonelukas
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-multimodal
Source: https://github.com/Stonelukas/Mouse-on-Numpad/tree/main/.opencode/skill/ai-multimodal
Command: npx skills add https://github.com/Stonelukas/Mouse-on-Numpad --skill ai-multimodal-stonelukas

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The AI Multimodal Skill tackles the challenge of extracting structured insights from diverse media by applying Gemini's multimodal capabilities to analyze images, audio, video, and documents, automating transcription, captioning, OCR, and content understanding.

Core Features & Use Cases

  • Multimodal analysis: Analyze images, audio, and video to produce captions, transcripts, and contextual notes.
  • Content generation: Generate images or short videos using Imagen 4 or Veo for visual assets or demonstrations.
  • OCR & document understanding: Extract text from PDFs/images and structure it for downstream workflows.
  • Workflow automation: Batch-process media, manage API keys with rotation, and run via CLI scripts for repeatable pipelines.

Quick Start

Provide a media file to the skill to perform multimodal analysis and optionally generate a corresponding media asset.

Frequently Asked Questions about ai-multimodal

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

FAQPage Schema
How do I extract text from images and PDFs using OCR?▼

You can perform OCR by providing a media file to the skill, which applies Gemini's multimodal API to analyze images and PDFs, extracting and structuring text for downstream workflows.

Can I transcribe audio and video files with Gemini multimodal models?▼

Yes, Gemini multimodal models can transcribe audio and video files. The skill processes these media types via the File API or inline data to generate accurate transcripts and contextual notes.

How do I batch process media files for transcription and captioning?▼

Batch process media for transcription and captioning by running the provided CLI scripts, which automate media analysis, manage API keys with rotation, and deliver outputs for repeatable pipelines.

What is the best way to generate images and short videos from text prompts?▼

Generating images and short videos from text prompts is achieved through the skill's content generation feature, utilizing Imagen 4 or Veo to create visual assets or demonstrations.

Does this multimodal analysis tool work with centralized API key resolution?▼

Yes, multimodal analysis supports centralized API key resolution. The skill manages keys with rotation using python-dotenv and operates via CLI scripts for setup and batch processing.

Related Skills

Explore More Design & Creative Skills→
locdinh209locdinh209

ai-multimodal

Process and generate multimedia content using the Google Gemini API.

Community
Advanced
bmad-labsbmad-labs
14

ai-multimodal

Process and generate multimedia content using Google Gemini models.

Official
Advanced
tara-shopostara-shopos
3

image_editing

Edit images via natural language prompts using the editImage tool.

Community
Intermediate
vneseyoungstervneseyoungster
27

ai-multimodal

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

Community
Advanced