skills.rest
vibery-studio
vibery-studioOFFICIAL
Explore all skills by this author →
GitHub

ai-multimodal

Unify audio, image, video, and document processing via Google Gemini multimodal API.

3|1|Updated Dec 21, 2025
Search Tags:#ai#multimodal#gemini#image-generation#video-analysis#audio-analysis#document-extraction
One-click install
npx skills add https://github.com/vibery-studio/templates --skill ai-multimodal-vibery-studio
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-multimodal
Source: https://github.com/vibery-studio/templates/tree/main/skills/ai-multimodal
Command: npx skills add https://github.com/vibery-studio/templates --skill ai-multimodal-vibery-studio

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

The ai multimodal skill provides a unified interface to analyze and generate content across audio, images, video, and documents using Google Gemini's multimodal API, enabling automation and faster insight.

Core Features & Use Cases

  • Transcribe audio with timestamps, summarize content, detect speakers, and analyze music or environment.
  • Analyze images with captioning, object detection, OCR, and questions answering; generate image outputs from prompts.
  • Process video for scene detection, transcription with visuals, Q&A, and YouTube URL support; handle long-form content.
  • Extract data from PDFs and other documents into structured formats; batch convert to markdown or JSON outputs.
  • Create new images or edit existing ones using text prompts; control aspect ratios and styles.

Quick Start

Upload a media file and prompt the skill to transcribe, caption, or generate an image using Gemini multimodal APIs to return results.

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 and detect speakers using a multimodal AI?▼

Multimodal AI transcription with timestamps analyzes audio via Google Gemini APIs to generate time-aligned text and speaker detection. It handles robust API key configuration and batch processing for reliable production use across audio files and inline data.

Can I extract data from PDFs and convert documents to structured JSON or markdown?▼

Document data extraction uses Google Gemini to parse PDFs and extract structured data into JSON or markdown formats. The skill supports batch processing and robust error handling to reliably convert multiple documents for downstream automation.

Does Google Gemini support video scene detection and Q&A from YouTube URLs?▼

Gemini multimodal API supports video scene detection, transcription with visuals, and Q&A, including direct YouTube URL processing. It handles long-form content and robust model configuration for reliable video analysis workflows.

What is the best way to generate and edit images from text prompts with specific aspect ratios?▼

Image generation and editing via Gemini multimodal API creates or modifies images from text prompts while controlling aspect ratios and styles. The skill unifies inline data and file inputs for robust image output production.

How do I perform OCR and object detection on images through an API?▼

Image analysis through Gemini multimodal API performs OCR, object detection, and captioning on uploaded files or URLs. The skill provides a unified interface for robust image Q&A and batch processing.

Do I need a Google Gemini API key to process audio, video, and images in one workflow?▼

A Google Gemini API key is required to unify audio, image, video, and document processing. The skill manages robust API key handling and model configuration via python-dotenv to ensure reliable multimodal automation.

Related Skills

Explore More Software Engineering Skills→
nguyenvanlinh1902nguyenvanlinh1902

ai-multimodal

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

Community
Advanced
jiunbaejiunbae
12

document-processor

Extract and convert text, tables, images, and metadata across PDF, DOCX, XLSX, PPTX formats.

Community
Advanced
TietveTietve
1

ai-multimodal

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

Community
Advanced
Junior-Frontend-devJunior-Frontend-dev

ai-multimodal

placeholder

Community
Advanced