skills.rest
nunomen
nunomenCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

fal-ai

Generate images, videos, and speech from text prompts via Python scripts.

1|Updated Dec 29, 2025
Search Tags:#text-to-speech#media#images#generate#videos#fal-ai
One-click install
npx skills add https://github.com/nunomen/claude-skills --skill fal-ai-nunomen
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: fal-ai
Source: https://github.com/nunomen/claude-skills/tree/main/fal-ai
Command: npx skills add https://github.com/nunomen/claude-skills --skill fal-ai-nunomen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires fal-client>=0.5.0, httpx>=0.27.0, and includes scripts (resource) components.

What problem does it solve?

Fal-ai provides a unified workflow to generate media assets—images, videos, and speech—from natural language prompts, accelerating content creation and prototyping.

Core Features & Use Cases

  • Text-to-Image: generate still imagery from descriptive prompts using a suite of models (flux-schnell, flux-pro, etc.).
  • Text-to-Video: create short videos from prompts (veo3, ltx, hunyuan, etc.).
  • Image-to-Video & Voice: animate existing imagery and synthesize speech or clone voices with TTS models (f5-tts, kokoro).
  • Use Case: rapidly produce marketing visuals, product demos, and tutorial media without external design tools.

Quick Start

To get started, set your API key and run the included scripts, for example:

  • export FAL_API_KEY="your-api-key-here"
  • uv run ./scripts/generate_image.py "A serene mountain landscape at sunset"
  • uv run ./scripts/generate_video_text.py "cinematic drone shot over mountains" --model hunyuan
  • uv run ./scripts/generate_speech.py "Welcome to our product demo." --model f5-tts

Frequently Asked Questions about fal-ai

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

FAQPage Schema
How do I generate images and videos from text prompts in Python?▼

Text-to-speech generation from prompts is executed by running Python scripts that pass text to TTS models like f5-tts or kokoro. The fal-client library handles the API requests to synthesize speech or clone voices, returning the resulting audio assets.

Do I need an API key to use fal-ai for media generation?▼

Yes, an API key is required. You must set the FAL_API_KEY environment variable to authorize API requests before executing any text-to-image, text-to-video, or text-to-speech generation scripts provided by the Skill.

Can I animate an existing image to create a video?▼

Yes, the Skill supports an image-to-video workflow that animates existing imagery. By passing your image and a prompt through the fal-client, models generate short animated videos from the static source material.

What is the best way to rapidly prototype marketing visuals without external design tools?▼

Generating media assets from natural language prompts provides a rapid prototyping workflow for marketing visuals. The Skill uses Python scripts and models like flux-pro or veo3 to create images, videos, and speech without external design tools.

Does this text-to-video approach work with different generation models?▼

Yes, the text-to-video and text-to-image workflows support multiple models. You can specify models such as hunyuan, veo3, ltx, flux-schnell, or flux-pro via CLI arguments to control the generation output.

Related Skills

Explore More Design & Creative Skills→
hieuckhieuck

fal-ai-media

Generate images, videos, and audio via fal.ai MCP.

Community
Advanced
labs21-devlabs21-dev
28

media

Generate images, videos, speech, and transcriptions via harness CLI commands.

Official
Intermediate
manashmandalmanashmandal

imggen

Generate images from text prompts using OpenAI image APIs and extract OCR text from images.

Community
Basic
sayasaya8039sayasaya8039
2

fal-ai-media

Generate images, videos, and audio through a unified fal.ai interface.

Community
Intermediate