skills.rest
liamtran96
liamtran96COMMUNITY
Explore all skills by this author →
GitHub

ai-multimodal

Analyze and generate multimedia content using Google Gemini multimodal APIs.

Updated Jan 30, 2026
Search Tags:#API integration#multimodal#Python#Gemini#audio transcription#image-generation
One-click install
npx skills add https://github.com/liamtran96/msm-car-booking --skill ai-multimodal-liamtran96
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-multimodal
Source: https://github.com/liamtran96/msm-car-booking/tree/main/.claude/skills/ai-multimodal
Command: npx skills add https://github.com/liamtran96/msm-car-booking --skill ai-multimodal-liamtran96

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 provides a unified interface to analyze and generate multimedia content by leveraging Google Gemini's multimodal capabilities, enabling automated workflow tasks across audio, image, video, and document data.

Core Features & Use Cases

  • Audio: transcription with timestamps, summarization, speech understanding, and speaker detection.
  • Vision: image captioning, object detection, OCR, visual question answering, segmentation, and multi-image comparison.
  • Video: scene detection, Q&A, temporal analysis, YouTube URL processing, and long-format processing.
  • Documents: PDF table and form extraction, document understanding, and structured data output.
  • Image generation and editing: text-to-image generation, style transfer, composition of multiple images, and iterative refinement for polished outputs.
  • Use Case: Build AI assistants that analyze media, automate asset generation, and streamline media workflows from raw media to ready-to-use insights.

Quick Start

Set GEMINI_API_KEY and install the google-genai package, then run one of the included scripts (e.g., gemini_batch_process.py or document_converter.py) to process a sample audio, image, video, or PDF file.

Frequently Asked Questions about ai-multimodal

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

FAQPage Schema
How do I build a Python pipeline for multimodal audio transcription and image generation?▼

You can build a Python multimodal pipeline for audio transcription and image generation using the google-genai library to interface with Gemini APIs. This skill processes audio, video, and documents, generating images and structured data from raw media.

Can I extract tables and forms from PDF documents using the Gemini API in Python?▼

Yes, you can extract tables and forms from PDF documents using the Gemini API in Python. This skill provides document understanding capabilities that parse PDFs into structured data outputs, automating data extraction workflows via the google-genai package.

What's the best way to analyze video content and detect scenes with Google Gemini?▼

The best way to analyze video content and detect scenes with Google Gemini is by using this skill's video analysis features. It supports temporal analysis, scene detection, long-format processing, and YouTube URL processing directly through the google-genai Python library.

Do I need a Gemini API key to run multimodal image captioning and OCR tasks?▼

Yes, you need a Gemini API key to run multimodal image captioning and OCR tasks. This skill requires the GEMINI_API_KEY configured via python-dotenv for local development, alongside the google-genai and Pillow dependencies to process visual data.

Does the google-genai Python library support text-to-image generation and style transfer?▼

Yes, the google-genai Python library supports text-to-image generation and style transfer through this skill. It enables composition of multiple images, iterative refinement, and polished outputs, allowing developers to automate asset generation workflows.

Related Skills

Explore More Software Engineering Skills→
Svenja-devSvenja-dev
38

gemini-image-gen

Generate branded images from prompts using Google's Gemini API.

Community
Intermediate
lv7devlv7dev

ai-multimodal

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

Community
Advanced
VoDaiLoczVoDaiLocz
24

ai-multimodal

Process and generate multimedia content using the Google Gemini API.

Community
Advanced
Thanh-aperoThanh-apero
1

ai-multimodal

Analyze, transcribe, OCR, and generate multimedia content via Google Gemini API.

Community
Advanced