media-generation

Generate images, video, music, sound effects, and voice from text prompts.

Updated Jun 20, 2026
One-click install
npx skills add https://github.com/4tie/fortiesr --skill media-generation-4tie
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: media-generation
Source: https://github.com/4tie/fortiesr/tree/main/.local/skills/media-generation
Command: npx skills add https://github.com/4tie/fortiesr --skill media-generation-4tie

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of sourcing and creating media by helping you generate custom visuals, audio, and video while also retrieving stock images when realism matters.

Core Features & Use Cases

  • Image generation: Create custom illustrations, concepts, placeholders, and polished visual assets from prompts.
  • Stock image retrieval: Find professional photography and real-world scenes for business, marketing, and product work.
  • Audio and video creation: Produce music, sound effects, voiceovers, and short video clips for presentations, apps, and social content.
  • Use case: Turn a rough product idea into a hero image, supporting stock photo, and short promo clip without leaving the workflow.

Quick Start

Ask the media-generation skill to create a widescreen landing-page hero image for a fintech product and retrieve two matching horizontal stock photos for the supporting section.

Frequently Asked Questions about media-generation

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

FAQPage Schema
How do I generate custom images and voiceovers from text prompts for a landing page?

To generate images and voiceovers from text prompts, provide structured prompts specifying the desired media type, valid output formats, and aspect ratios. This approach reliably produces custom visuals, music, and voice assets for creative production workflows.

Can I retrieve real-world stock photos instead of AI-generated images for marketing content?

Yes, you can retrieve professional stock photos instead of AI-generated images when realism matters. The workflow supports sourcing real-world photography for business and marketing content alongside custom generated visual assets.

What is the best way to create short video clips and sound effects for app prototyping?

The best way to create short video clips and sound effects is using structured text prompts that specify the required media type and valid aspect ratios. This generates usable audio and video assets directly for app prototyping.

Do I need reference files to produce usable media assets reliably?

No, reference files are optional for producing usable media assets reliably. You primarily need structured text prompts, valid output formats, and specified aspect ratios to generate images, audio, and video successfully.

What are the limitations when generating media for different aspect ratios and output formats?

The main limitation when generating media is that valid output formats and aspect ratios must be explicitly specified in the prompt. Without these structured inputs, the workflow cannot reliably produce usable assets across image, video, and audio types.

Can a media generation workflow assemble a complete hero image, supporting photo, and promo clip?

Yes, a media generation workflow can assemble a complete hero image, supporting stock photo, and short promo clip. By combining AI-generated visuals and stock retrieval, it turns rough product ideas into assembled content.