fal-ai-media

Generates images, videos, and audio through fal.ai MCP models.

1|Updated Oct 11, 2025
One-click install
npx skills add https://github.com/ibytechaos/claude --skill fal-ai-media-ibytechaos
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fal-ai-media
Source: https://github.com/ibytechaos/claude/tree/main/plugins/everything-claude-code/skills/fal-ai-media
Command: npx skills add https://github.com/ibytechaos/claude --skill fal-ai-media-ibytechaos

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires fal-ai-mcp-server.

What problem does it solve? Creating AI-generated media requires navigating dozens of models with different parameters, pricing, and capabilities. This Skill consolidates image, video, and audio generation into a single workflow via the fal.ai MCP server, so you can produce media without learning each model's API. ## Core Features & Use Cases - Image Generation: Text-to-image and image editing with Nano Banana 2 for fast drafts and Nano Banana Pro for high-fidelity production output. - 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 controls. - Audio Generation: Conversational text-to-speech with CSM-1B, video-to-audio with ThinkSound, plus ElevenLabs and VideoDB integration options. - Cost Control: Estimate generation costs before running expensive jobs and discover models via search. - Use Case: A content creator needs a thumbnail, a 5-second intro clip, and voiceover narration for a video. They generate the thumbnail with Nano Banana 2, animate it with Seedance, and produce the narration with CSM-1B, all from one conversation. ## Quick Start Configure the fal.ai MCP server with your FAL_KEY, then ask the AI to generate a landscape image of a sunset cityscape using Nano Banana 2.

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 in Claude?

Configure the fal.ai MCP server in ~/.claude.json with your FAL_KEY, then call the generate tool with an app_id like fal-ai/nano-banana-2 and a prompt. You can control aspect ratio, image count, seed, and guidance scale through input_data parameters.

What is the difference between Nano Banana 2 and Nano Banana Pro?

Nano Banana 2 is optimized for fast iterations, drafts, and image editing tasks. Nano Banana Pro targets production images with higher fidelity, realism, typography, and detailed prompt adherence. A common workflow iterates on Nano Banana 2, then switches to Pro for finals.

Which fal.ai model should I use for text-to-video generation?

Seedance 1.0 Pro handles text-to-video and image-to-video with high motion quality. Kling Video v3 Pro adds native audio generation, and Veo 3 produces video with generated sound and high visual quality. All support 5s or 10s durations and multiple aspect ratios.

Can I generate speech or sound effects with fal.ai?

Yes. CSM-1B provides conversational text-to-speech, and ThinkSound generates matching audio from video content. For professional voice synthesis, the Skill also documents direct ElevenLabs API usage and VideoDB generative audio for voice, music, and sound effects.

How do I estimate fal.ai generation costs before running a job?

Call the estimate_cost MCP tool with estimate_type set to unit_price and the target endpoint with its unit quantity. This returns the expected cost before you commit to expensive operations like video generation.

Why is my fal.ai generation not working in Claude?

The most common cause is a missing or misconfigured fal.ai MCP server. Verify the server entry exists in ~/.claude.json with a valid FAL_KEY environment variable obtained from fal.ai, and confirm the npx fal-ai-mcp-server package can launch.