media-generation

Generate AI images, videos, music, and speech, and retrieve stock images.

Updated May 17, 2026
One-click install
npx skills add https://github.com/Amna-exe/EventFlow_App --skill media-generation-amna-exe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: media-generation
Source: https://github.com/Amna-exe/EventFlow_App/tree/main/Final-MAD-project-main-4zipzipzipzipzip-1-ite1zipzip/.local/skills/media-generation
Command: npx skills add https://github.com/Amna-exe/EventFlow_App --skill media-generation-amna-exe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating visual and audio assets for apps, websites, and content projects normally requires design tools, stock subscriptions, or manual media production. This Skill generates custom images, videos, music, sound effects, and speech from text prompts, and retrieves licensed stock images, all saved directly to local asset folders. ## Core Features & Use Cases - AI Image Generation: Generate up to 10 custom PNG images per call with control over aspect ratio, negative prompts, and background removal, synchronously or asynchronously. - Stock Image Retrieval: Fetch up to 10 licensed stock photos matching a description with orientation filtering. - Video, Music, and Audio Generation: Create short video clips (up to 8 seconds), music tracks (up to 600 seconds), sound effects (up to 30 seconds), and text-to-speech voiceovers via the companion reference documents. - Use Case: Building a landing page and need a hero image, background music, and a short product demo clip? Generate all three assets from text prompts and have them saved to attached_assets/ ready to reference in your code. ## Quick Start Generate a 16:9 hero image of a mountain landscape at sunset and save it as hero.png in my project's assets folder.

Frequently Asked Questions about media-generation

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

FAQPage Schema
How do I generate AI images from a text prompt?

Call generateImage with an images array containing objects with a prompt and an outputPath ending in .png. You can generate up to 10 images per call and optionally set aspectRatio, negativePrompt, and removeBackground.

How do I generate music or sound effects from text?

Use generateMusic for tracks up to 600 seconds or generateSoundEffect for clips up to 30 seconds, both taking a text prompt. Outputs save as MP3 or OGG files, with options for duration, looping, and audio format.

What image formats and aspect ratios are supported?

Generated images must be saved as PNG; .jpg, .jpeg, and .webp extensions cause errors. Supported aspect ratios are 1:1, 3:4, 4:3, 9:16, and 16:9, defaulting to 1:1.

When should I use stock images instead of AI-generated images?

Use stockImage when you need authentic professional photography, real-world scenes, people, or corporate imagery. Use generateImage for custom illustrations, specific visual concepts, or placeholder graphics not available in stock libraries.

What are the limitations of AI video generation?

Generated videos are limited to 8 seconds maximum, with duration options of 4, 6, or 8 seconds. Videos support 16:9 or 9:16 aspect ratios at 720p or 1080p resolution, and text rendered in generated media is not reliable.

Why does generateImage fail with an images field required error?

This error occurs when parameters are passed flat instead of wrapped in the images array. Even for a single image, you must pass images as a list containing one request object with prompt and outputPath.