skills.rest
PhucMPham
PhucMPhamCOMMUNITY
Explore all skills by this author →
GitHub

ai-multimodal

Coordinate Gemini multimodal API tasks for audio, images, video, and documents.

Updated Dec 25, 2025
Search Tags:#multimodal#content-generation#Gemini API#video-analysis#image-analysis#audio-processing#document-extraction
One-click install
npx skills add https://github.com/PhucMPham/threejs-christmas-tree --skill ai-multimodal-phucmpham
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-multimodal
Source: https://github.com/PhucMPham/threejs-christmas-tree/tree/main/.claude/skills/ai-multimodal
Command: npx skills add https://github.com/PhucMPham/threejs-christmas-tree --skill ai-multimodal-phucmpham

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables end-to-end multimodal processing using Gemini and related models to analyze, transcribe, extract, and generate content from audio, images, video, and documents, reducing manual toil and enabling richer AI-driven media workflows.

Core Features & Use Cases

  • Audio/Video analysis: Transcription with timestamps, summarization, scene detection, and YouTube processing (up to hours long).
  • Image understanding: Captioning, object detection, segmentation, OCR, and multi-image comparisons.
  • Document understanding: PDF extraction of tables, forms, charts, and diagrams.
  • Generation: Text-to-image and text-to-video generation with Imagen 4 and Veo 3, plus editing and refinement.
  • Model & key management: Supports Google Gemini, Imagen, and Veo models with rotation and orchestration.

Quick Start

Example: Analyze an image python3 gemini_batch_process.py --task analyze --files sample.jpg

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 video with timestamps using Gemini?▼

Gemini's multimodal API automatically transcribes audio and video files, extracting text with temporal markers. This Skill orchestrates that process for files up to hours long, including YouTube inputs, and outputs structured JSON with timing metadata for downstream indexing or editing.

Can I extract text and tables from PDFs using Gemini?▼

Yes. Gemini's document understanding analyzes PDF pages to extract tables, forms, charts, and diagrams as structured data. This Skill handles batch processing and format conversion, returning JSON or text output ready for further analysis or export.

What's the best way to analyze images—captioning, OCR, and object detection?▼

Image analysis with Gemini performs captioning, optical character recognition, object detection, and segmentation in a single call. This Skill supports inline data, URLs, and file uploads, letting you process single or multiple images and combine results into structured reports.

Does this support text-to-image and text-to-video generation?▼

Yes. This Skill integrates Imagen 4 for image generation and Veo 3 for video generation from text prompts, plus editing and refinement workflows. It handles model orchestration, billing tracking, and batch operations across generation tasks.

How do I rotate API keys and manage multiple Gemini models?▼

This Skill includes tooling for API key rotation, model orchestration across Gemini, Imagen, and Veo, and batch processing coordination. Setup utilities configure credentials via environment variables, and the framework handles tokenization and billing considerations automatically.

Can I process YouTube videos directly or only local files?▼

Both. This Skill accepts YouTube URLs for transcription, scene detection, and temporal analysis alongside local audio and video files. It processes long-form content with timestamp alignment and outputs structured results for summarization or scene-based editing.

Related Skills

Explore More Software Engineering Skills→
danielctcdanielctc

ai-multimodal

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

Community
Advanced
omosb1-sysomosb1-sys

precision-extractor

Convert unstructured text into structured JSON/TOON assets with entity resolution.

Community
Advanced
themadorgthemadorg
6

bedrud-jobs

Coordinate asynchronous tasks, scheduling, and cleanup for Bedrud deployments.

Official
Advanced
vinwangvinwang

cost-aware-llm-pipeline

Route LLM tasks to cost-effective models and track API spend.

Community
Advanced