skills.rest
luan-thnh
luan-thnhCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ai-multimodal

Analyze audio, images, videos, and documents with Gemini, Imagen, and Veo APIs.

Updated Jan 31, 2026
Search Tags:#ai#multimodal#gemini#batch-processing#document-extraction#media-analysis
One-click install
npx skills add https://github.com/luan-thnh/hrm-auto-extension --skill ai-multimodal-luan-thnh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-multimodal
Source: https://github.com/luan-thnh/hrm-auto-extension/tree/main/.opencode/skills/ai-multimodal
Command: npx skills add https://github.com/luan-thnh/hrm-auto-extension --skill ai-multimodal-luan-thnh

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

ai-multimodal provides a unified toolkit to process and generate multimedia content across audio, images, video, and documents using Google Gemini, Imagen, and Veo APIs. It enables automated media understanding, content creation, and data extraction at scale, helping teams accelerate workflows that rely on rich media insights.

Core Features & Use Cases

  • Audio transcription with timestamps and visual context extraction for videos and streams.
  • Image understanding and editing including captioning, object detection, OCR, and multi-image comparison.
  • Video analysis and generation with scene detection, Q&A, and 8-second native-audio clips.
  • Document extraction and conversion from PDFs and office documents to markdown/text outputs.
  • Batch processing and orchestration across media types with robust error handling and key management.

Quick Start

Run a sample batch to analyze media by executing python scripts/gemini_batch_process.py --task analyze --input sample1.jpg sample2.jpg.

Frequently Asked Questions about ai-multimodal

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

FAQPage Schema
How do I automate batch processing for multimodal media analysis?▼

Automate multimodal media analysis by executing the batch processing script to analyze audio, images, videos, and documents, providing scalable content understanding and data extraction across mixed media types.

Can I extract text and convert PDFs to markdown using Gemini APIs?▼

Yes, document extraction converts PDFs and office documents into markdown text outputs using Gemini APIs, enabling automated transformation of archival data into readable formats for downstream workflows.

How do I transcribe audio with timestamps and analyze video scenes?▼

Transcribe audio with timestamps and analyze video scenes by routing media files through Gemini and Veo models, producing visual context extraction, scene detection, and Q&A outputs for streams.

Does this multimodal toolkit support image understanding and editing?▼

Yes, image understanding and editing supports captioning, object detection, OCR, and multi-image comparison using Imagen and Gemini, generating descriptive text and edited visual outputs from input images.

What do I need to set up before running multimodal media processing scripts?▼

Setup requires configuring API keys via python-dotenv, selecting appropriate Gemini, Imagen, or Veo models, and ensuring proper handling of file sizes for batch processing across media types.

Are there limitations when generating 8-second native-audio video clips?▼

Video generation produces 8-second native-audio clips using Veo models, requiring strict file size handling and robust error management to prevent batch processing failures across large media orchestration tasks.

Related Skills

Explore More Software Engineering Skills→
Hoang130203Hoang130203

ai-multimodal

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

Community
Advanced
miles990miles990
20

content-platforms

Develop content management systems with TypeScript content modeling and Tiptap editing.

Community
Advanced
IoT-VNIoT-VN

ai-multimodal

Process media and documents with Gemini API for analysis, transcription, and generation.

Community
Advanced
haidonglethqbhaidonglethqb

ai-multimodal

Analyze images, audio, and video with the Gemini API.

Community
Advanced