skills.rest
lv7dev
lv7devCOMMUNITY
Explore all skills by this author →
GitHub

ai-multimodal

Analyze and generate audio, image, video, and document content with Gemini models.

Updated Feb 3, 2026
Search Tags:#image#multimodal#video#audio#generation#gemini#document
One-click install
npx skills add https://github.com/lv7dev/shop_v2 --skill ai-multimodal-lv7dev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-multimodal
Source: https://github.com/lv7dev/shop_v2/tree/main/.claude/skills/ai-multimodal
Command: npx skills add https://github.com/lv7dev/shop_v2 --skill ai-multimodal-lv7dev

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a unified interface to analyze and generate multimedia content across audio, image, video, and document formats using Google's Gemini multimodal APIs. It enables automated transcription, captioning, object detection, OCR, video scene analysis, and image generation, reducing manual effort and enabling multimodal AI workflows.

Core Features & Use Cases

  • Audio processing: transcription with timestamps, summarization, speech understanding, and TTS where applicable.
  • Image understanding: captioning, object detection with bounding boxes, segmentation, OCR, and visual Q&A.
  • Video analysis: scene detection, Q&A, temporal analysis, YouTube URL support, long-form video processing.
  • Document extraction: tables, forms, charts from PDFs; multi-page understanding; data extraction.
  • Image generation: text-to-image, editing, composition, refinement with various aspect ratios and styles.
  • Works with multiple Gemini models (Gemini 2.5/2.0) with large context windows.

Quick Start

Use the ai-multimodal skill to transcribe an audio file, summarize it, caption images, and generate a related image from a prompt.

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 with timestamps using Gemini?▼

Audio transcription with timestamps is automated by sending audio files to Gemini multimodal APIs, which process the speech and return text paired with precise time codes.

How do I extract tables and charts from PDFs?▼

PDF data extraction is handled by feeding documents into the Gemini API, which uses large context windows to parse multi-page files and output structured tables, forms, and charts.

Can I analyze long-form video and perform scene-based Q&A?▼

Video analysis supports scene detection and temporal Q&A by processing long-form video through Gemini models, allowing you to query specific visual events and extract contextual insights.

Does this approach work with multiple media formats in one workflow?▼

Multimodal media analysis unifies audio, image, video, and document processing within a single interface, enabling you to chain tasks like transcribing audio and generating related images.

What are the limitations of multimodal document processing?▼

Multimodal document processing depends on Gemini API context limits, so while it supports up to 2M tokens for large files, extremely dense PDFs may require chunking to ensure accurate extraction.

Do I need Python libraries like Pillow and python-docx to process media?▼

Python libraries such as Pillow, pypdf, and python-docx are required dependencies to handle local file manipulation, format conversion, and document parsing before API submission.

Related Skills

Explore More Design & Creative Skills→
nguyenvanlinh1902nguyenvanlinh1902

ai-multimodal

Extract insights from images, audio, and video using Gemini multimodal APIs.

Community
Advanced
Junior-Frontend-devJunior-Frontend-dev

ai-multimodal

placeholder

Community
Advanced
ddarkrddarkr
5

oma-pdf

Convert PDF files into structured Markdown with text, tables, headings, and images.

Community
Intermediate
toanalientoanalien

ai-multimodal

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

Community
Advanced