skills.rest
hhopkins95
hhopkins95COMMUNITY
Explore all skills by this author →
GitHub

ai-multimodal

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

Updated Dec 3, 2025
Search Tags:#multimodal#audio#Gemini#image-generation#video-analysis
One-click install
npx skills add https://github.com/hhopkins95/agent-plugins --skill ai-multimodal-hhopkins95
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-multimodal
Source: https://github.com/hhopkins95/agent-plugins/tree/main/plugins/ai-multimodal/skills/ai-multimodal
Command: npx skills add https://github.com/hhopkins95/agent-plugins --skill ai-multimodal-hhopkins95

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a unified interface to process and generate multimedia content using Google Gemini's multimodal API. It streamlines working with audio, images, videos, documents, and generated outputs, reducing manual context switching, speeding up media workflows, and lowering complexity.

Core Features & Use Cases

  • Audio Processing & Transcription: Transcribe audio with timestamps, summarize content, and generate speech.
  • Vision & Image Understanding: Caption images, detect objects, perform OCR, answer questions about visuals, and segment scenes.
  • Video Analysis: Detect scenes, generate video Q&A, summarize hours of footage, and support YouTube URLs.
  • Document Extraction: Extract text and structured data from PDFs and office documents.
  • Image Generation: Create images from prompts, edit and compose multiple inputs, and iteratively refine outputs.
  • Use cases: Convert long videos into concise, timestamped summaries; extract data from documents and images; batch generate marketing visuals from text prompts; build multimodal pipelines that operate across media types.

Quick Start

Use the ai-multimodal skill to process a sample set of media files: transcribe an audio, caption an image, extract text from a PDF, and generate a mood-board image from prompts.

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 files and extract text using Gemini's multimodal API?▼

Transcribe audio with Gemini's multimodal API by uploading audio files to extract text, timestamps, and summaries. The skill processes audio natively and outputs structured JSON or Markdown transcripts.

Can I analyze images, videos, and PDFs in a single workflow?▼

Yes, this skill processes multimedia across audio, images, video, and documents in unified workflows. Perform captioning, object detection, OCR, Q&A, and data extraction on multiple file types simultaneously.

How do I batch process media files and generate images from prompts?▼

Use batch workflows to process multiple media files at scale and generate images from text prompts with controls for aspect ratio, style, and quality. Output results as structured JSON or Markdown.

Does this work with large documents and long videos?▼

Yes, the skill handles context windows up to 2M tokens, supporting hours of video footage, multi-page PDFs, and office documents for summarization, extraction, and analysis.

What dependencies do I need to process multimedia with Gemini?▼

You need google-genai for API access, python-dotenv for credential management, and Pillow for image processing. These dependencies enable audio transcription, vision analysis, and image generation.

Can I extract structured data from images and PDFs?▼

Yes, extract text and structured data from PDFs, office documents, and images using OCR and document parsing. Results are output as JSON or Markdown for downstream processing.

Related Skills

Explore More Design & Creative Skills→
brixtonphambrixtonpham

ai-multimodal

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

Community
Advanced
marcoamumarcoamu
1

data_exporter

Export data from databases or files into CSV, JSON, Markdown, or HTML formats.

Community
Intermediate
pradyumnasagarpradyumnasagar
6

agent-handoff

Automate inter-skill data transfer and provenance capture via JSON Material Passports.

Community
Advanced
toanalientoanalien

ai-multimodal

Process audio, images, and video using Gemini's multimodal capabilities.

Community
Advanced