Runway Skills

Agent skills for the Runway API - generate AI videos, images, and audio.

Available Skills

Runway API

Complete skill for the Runway API covering video generation, image generation, and audio generation.

Video Generation:

• Gen-4.5 (latest) - Text-to-video and image-to-video
• Gen-4 Turbo - Fast image-to-video
• Gen-4 Aleph - Video-to-video transformation
• Act-Two - Character performance
• Google Veo - Text/image-to-video with audio

Image Generation:

• Gen-4 Image - High-quality text-to-image with style references
• Gen-4 Image Turbo - Fast iteration
• Gemini 2.5 Flash - Google image generation

Audio Generation (ElevenLabs):

• Text-to-Speech - Natural voice synthesis
• Sound Effects - Generate audio from descriptions
• Voice Isolation - Remove background noise
• Voice Dubbing - Translate audio to 28+ languages
• Speech-to-Speech - Voice conversion

Install:

claude skill add runwayml/skills/api

View Documentation

---

Installation

Install the Runway API Skill

claude skill add runwayml/skills/api

Install All Skills

claude skill add runwayml/skills

Configuration

Set your Runway API key as an environment variable:

export RUNWAYML_API_SECRET="your_api_key_here"

Get your API key at dev.runwayml.com.

SDK Support

Python

pip install runwayml

Node.js

npm install @runwayml/sdk

Quick Example

from runwayml import RunwayML

client = RunwayML()

# Text-to-video with latest Gen-4.5 model
task = client.text_to_video.create(
    model="gen4.5",
    prompt_text="A serene mountain lake at sunrise with mist rising",
    ratio="1280:720",
    duration=10
).wait_for_task_output()

print(f"Video URL: {task.output[0]}")

Documentation

• Complete API Documentation
• Model Guide
• Developer Portal (API keys & account)

License

MIT