ShortApi Video Models Aggregation Skill for Openclaw

A unified entry point to discover and integrate multiple high-end AI video generation models through a single API.

isdyh01
v1.0.3
Mar 20, 2026
2
978
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install shortapi-ai-video-generation

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install shortapi-ai-video-generation using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is ShortApi Video Models Aggregation Skill?

The ShortApi Video Models Aggregation Skill serves as a centralized gateway for developers to access a diverse range of AI video generation technologies. By leveraging Openclaw Skills, this tool simplifies the complexity of interacting with different providers like Google, Bytedance, and Alibaba. It eliminates the need for managing multiple API integrations by providing a standardized interface for text-to-video, image-to-video, and video extension tasks.

This skill is designed to ensure technical accuracy by requiring agents to fetch dynamic schemas for each specific model. This approach prevents parameter hallucination and ensures that every request—whether for a cinematic Veo 3.1 shot or a Kling O1 transformation—is perfectly structured according to the provider's latest requirements.

ShortApi Video Models Aggregation Skill Use Cases

  • Automating the creation of cinematic marketing videos from text descriptions.
  • Extending existing video clips using advanced AI temporal consistency.
  • Generating high-fidelity video content from static first and last frames for smooth transitions.
  • Building multi-model video generation workflows within AI agents using Openclaw Skills.
  • Transforming existing video styles using video-to-video inference models.

How ShortApi Video Models Aggregation Skill Works

  1. Verify the presence of a SHORTAPI_KEY to ensure authorized access to the inference endpoints.
  2. Identify the desired model ID from the supported list (e.g., google/veo-3.1/text-to-video).
  3. Fetch the mandatory model-specific skill document from the ShortApi schema registry to retrieve the exact parameter requirements.
  4. Construct a JSON payload mapping user inputs to the model-specific arguments (e.g., duration, aspect_ratio, or prompt).
  5. Submit the generation job to the unified ShortApi job creation endpoint.
  6. Poll the job status API in the background using the returned job_id until the generation is complete.
  7. Render the final video result inline using HTML5 video tags for immediate user preview.

ShortApi Video Models Aggregation Skill Setup

To use this skill within the Openclaw Skills ecosystem, ensure your environment is configured with your API key:

# Export your ShortApi API key
export SHORTAPI_KEY='your_api_key_here'

# Example: Fetching a model schema before generation
curl -X GET https://shortapi.ai/api/skill/google/veo-3.1/text-to-video

ShortApi Video Models Aggregation Skill Data Schema & Taxonomy

The skill utilizes a structured request-response pattern to manage video generation jobs:

Field Type Description
model String The unique model identifier (e.g., kwaivgi/kling-3.0/text-to-video)
args Object Model-specific parameters defined by the fetched schema
callback_url String Optional URL for webhook notifications upon job completion
job_id String The unique identifier returned to track generation progress

ShortApi Video Models Aggregation Skill Advanced Features

  • Dynamic Schema Discovery: Automatically fetches the latest API signatures to support new models without code changes.
  • Background Polling Logic: Built-in state management to handle long-running video generation tasks asynchronously.
  • Multi-Provider Support: Access Veo, Kling, Vidu, Pixverse, and Wan models through a single Openclaw Skills interface.
  • Inline Media Rendering: Proactively renders HTML5 video and audio players directly in the agent chat interface for immediate feedback.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*