
fal.ai Media Generation
Generate images, videos and audio with AI models via the fal.ai MCP server
- Repository
- affaan-m/ECC
- Stars
- 295,127
- Licence
- MIT
- Files
- 2 files
What it does
Once installed, the agent can create images, videos and audio on request by calling fal.ai's hosted AI models through an MCP server (a connector that lets the agent use outside tools). It guides the agent to pick a model, estimate cost before running, and handle image-to-video or image editing. Some sections also show direct calls to ElevenLabs and VideoDB APIs for voice and music, which need their own keys.
Great for
- Creators who want quick drafts of thumbnails, product images or short clips
- Marketers producing social media visuals or narration without a studio
- Developers prototyping media generation inside an agent workflow
Skip it if
- Use where generated media must be guaranteed original or rights-cleared, since the file does not describe model licensing terms and outputs may resemble existing works
- Projects with a tight budget and no cost checks, because video generation can be expensive and the skill relies on the user to run estimate_cost
- Anyone unwilling to store an API key in a config file, since setup requires putting FAL_KEY in ~/.claude.json
Try asking
- “Generate a 16:9 cyberpunk cityscape image for my blog header”
- “Turn this product photo into a 5-second video with a slow zoom out”
- “Create a short narration in a calm voice for my tutorial intro”
- “Estimate the cost of a 10-second video before generating it”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 2 original files, the MIT licence and an attribution note.
fal-ai-media.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip fal-ai-media.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip fal-ai-media.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Iterate with the cheaper Nano Banana 2 model and switch to Nano Banana Pro only for final images
- Use the seed parameter to reproduce results while refining prompts
- Run estimate_cost before any video generation and keep the API key out of shared files
What's inside
- agents/openai.yaml
- SKILL.md
Redistributed unmodified from affaan-m/ECC under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.