skills.rest
ovisan
ovisanCOMMUNITY
Explore all skills by this author →
GitHub

fal-ai-media

Generate images, videos, and audio using fal.ai models via MCP tools.

2|Updated Mar 29, 2015
Search Tags:#image generation#mcp#text-to-speech#video generation#ai models#media generation#fal.ai
One-click install
npx skills add https://github.com/ovisan/dotfiles --skill fal-ai-media-ovisan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: fal-ai-media
Source: https://github.com/ovisan/dotfiles/tree/main/.agents/skills/fal-ai-media
Command: npx skills add https://github.com/ovisan/dotfiles --skill fal-ai-media-ovisan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating AI-generated media requires navigating dozens of models with different parameters, pricing, and capabilities. This Skill provides a unified workflow for generating images, videos, and audio through the fal.ai MCP server, with concrete parameter references and cost estimation. ## Core Features & Use Cases - Image Generation: Text-to-image and image editing with Nano Banana 2 and Nano Banana Pro, including aspect ratio, seed, and guidance scale controls. - Video Generation: Text-to-video and image-to-video using Seedance 1.0 Pro, Kling Video v3 Pro, and Veo 3, with duration and aspect ratio options. - Audio Generation: Text-to-speech with CSM-1B, video-to-audio with ThinkSound, plus ElevenLabs and VideoDB alternatives. - Use Case: A content creator needs a thumbnail, a short promo clip, and a voiceover for a video. Use this Skill to generate the image with Nano Banana Pro, animate it with Seedance, and synthesize narration with CSM-1B, checking costs before each run. ## Quick Start Configure the fal.ai MCP server with your FAL_KEY, then ask the AI to generate an image of a specific scene using the fal-ai nano-banana model.

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 with fal.ai?▼

Use the generate MCP tool with app_id fal-ai/nano-banana-2 for fast drafts or fal-ai/nano-banana-pro for high-fidelity output. Pass a prompt, image_size such as landscape_16_9, and optionally num_images, seed, and guidance_scale.

How to create video from text or images with fal.ai models?▼

Call generate with fal-ai/seedance-1-0-pro, fal-ai/kling-video/v3/pro, or fal-ai/veo-3 and provide a prompt, duration of 5s or 10s, and aspect_ratio. For image-to-video, upload a source image first and pass its URL as image_url.

What MCP tools does the fal.ai server provide?▼

The fal.ai MCP server provides search, find, generate, result, status, cancel, estimate_cost, models, and upload tools. These cover model discovery, running generations, checking async job status, and estimating costs before execution.

Does fal.ai media generation require an API key?▼

Yes, you need a FAL_KEY from fal.ai configured in the MCP server environment variables. Add the fal-ai server entry to ~/.claude.json with the key in the env block before using any generation tools.

How do I estimate fal.ai generation cost before running?▼

Use the estimate_cost tool with estimate_type unit_price and specify the endpoint with unit_quantity. This returns the expected cost so you can avoid running expensive video generations blindly.

When should I use ElevenLabs instead of fal.ai for speech?▼

Use ElevenLabs directly via its REST API when you need professional voice synthesis with voice settings like stability and similarity_boost. It is not available through the fal.ai MCP server and requires a separate ELEVENLABS_API_KEY.

Related Skills

Explore More Design & Creative Skills→
openaiopenai
5.3k

adobe-edit-quick-cut

Generates three AI-edited sizzle reel variations from an uploaded video using Adobe Quick Cut.

Official
Advanced
apexradiusapexradius

video-produce

Automate video production with Gemini API and ffmpeg.

Official
Advanced
digirati-co-ukdigirati-co-uk
57

media-assets

Automate media upload, validation, storage, and thumbnail generation for Madoc TS assets.

Official
Intermediate
storyclaw-officialstoryclaw-official

elevenlabs-tts

Convert text to ogg_opus speech via the ElevenLabs API.

Official
Intermediate