fal-ai-media

Generate images, videos, and audio from text prompts via fal.ai MCP.

Updated Apr 25, 2026
One-click install
npx skills add https://github.com/ldk-hub/broke-shopping --skill fal-ai-media-ldk-hub
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fal-ai-media
Source: https://github.com/ldk-hub/broke-shopping/tree/main/.agent/.agents/skills/fal-ai-media
Command: npx skills add https://github.com/ldk-hub/broke-shopping --skill fal-ai-media-ldk-hub

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

fal.ai MCP enables unified generation of images, videos, and audio from natural language prompts, accelerating creative workflows.

Core Features & Use Cases

  • Image generation from text prompts using fal.ai Nano Banana models
  • Video generation from prompts or existing visuals using Seedance, Kling, and Veo 3
  • Text-to-speech with CSM-1B and video-to-audio via ThinkSound
  • Rapid prototyping for marketing assets, product demos, and content creation

Quick Start

Provide a text prompt and select a fal.ai model to generate images, video, or audio.

Frequently Asked Questions about fal-ai-media

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

FAQPage Schema
How do I generate images and video from text prompts using fal.ai?

To generate images and video from text prompts using fal.ai, provide a natural language prompt and select a model like Nano Banana or Veo 3. This requires configuring the MCP server in ~/.claude.json with a valid API key to execute the workflow.

Can I add audio narration to an existing video using text-to-speech?

Yes, you can add audio to video using text-to-speech. The fal.ai MCP supports speech generation with CSM-1B and video-to-audio via ThinkSound, allowing you to create audio narration for character animation or product demos.

Do I need an API key to run fal.ai media generation workflows?

Yes, an API key is required to run fal.ai media generation workflows. You must configure the MCP server via the ~/.claude.json file with a valid fal.ai API key to execute generation and cost-estimation tasks successfully.

What is the best way to rapidly prototype marketing visuals with AI?

The best way to rapidly prototype marketing visuals with AI is using unified text-to-image and text-to-video generation. By using fal.ai models like Seedance and Kling, you can accelerate creative workflows and generate assets from natural language prompts.

What are the limitations of using fal.ai MCP for media generation?

Limitations of using fal.ai MCP include its dependency on specific models like Nano Banana, Seedance, and Veo 3, and the requirement of an active API key. It is constrained by the cost-estimation workflows and MCP server configuration defined in ~/.claude.json.

Does fal-ai-media support text-to-video generation for quick content creation?

Yes, fal-ai-media supports text-to-video generation for quick content creation. It uses models like Seedance, Kling, and Veo 3 to generate video from natural language prompts, making it applicable for rapid prototyping and marketing visuals.