An automated production pipeline that transforms a single topic or idea into a fully edited 60-90 second vertical video delivered via Telegram.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install video-full-free
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install video-full-free 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 Short-Video-AI Pipeline?
Short-Video-AI is a sophisticated automation workflow designed for the Openclaw Skills ecosystem. It streamlines the complex process of video production by integrating multiple state-of-the-art AI models. From a simple text prompt, the skill generates a synchronized script, high-quality cinematic clips using Wan2.6, and professional voiceovers via ElevenLabs.
This skill eliminates the manual labor of video editing, allowing developers and content creators to generate vertical content (9:16) for Reels, Shorts, and TikToks at scale. By leveraging FFmpeg for backend processing, it ensures that every visual scene is perfectly timed with its corresponding audio before being delivered directly to a designated Telegram chat.
Short-Video-AI Pipeline Use Cases
- Rapid creation of educational or informative social media shorts.
- Automated news summaries or daily fact videos.
- Prototyping visual content for marketing campaigns.
- Generating localized video content in multiple languages with high-quality TTS.
- Scaling video production for faceless YouTube or TikTok channels.
How Short-Video-AI Pipeline Works
- The user provides a topic, language, and preferred style to the Openclaw Skills agent.
- An LLM generates a structured JSON script featuring 6-9 scenes, including visual descriptions and voiceover text.
- The pipeline calls the Wan2.6 model via HuggingFace or Fal.ai to generate 10-second cinematic video clips for each scene.
- ElevenLabs TTS converts the script text into high-quality audio files using the eleven_multilingual_v2 model.
- FFmpeg merges the individual video and audio files, then concatenates all scenes into a final MP4 project.
- The completed video is uploaded and sent to the user through the Telegram Bot API with a detailed caption.
Short-Video-AI Pipeline Setup
To deploy this skill within your Openclaw Skills environment, you must configure the following environment variables:
# API Configuration
export HUGGINGFACE_API_TOKEN=hf_xxxxxxxxxxxxxxxxxxxx
export ELEVENLABS_API_KEY=sk_xxxxxxxxxxxxxxxxxxxx
export ELEVENLABS_VOICE_ID=xxxxxx
export TELEGRAM_BOT_TOKEN=xxxx:xxxxxxxx
export TELEGRAM_CHAT_ID=xxxxxxxxx
# System Requirements
sudo apt-get install ffmpeg
Short-Video-AI Pipeline Data Schema & Taxonomy
The skill organizes every video generation task into a specific project directory with the following structure:
| File Name | Description |
|---|---|
script.json |
The full AI-generated script including scene metadata. |
scene_XX.mp4 |
Raw video output from Wan2.6 for specific scenes. |
vo_XX.mp3 |
Voiceover audio generated by ElevenLabs. |
merged_XX.mp4 |
Intermediate files combining video and audio per scene. |
[project]_final.mp4 |
The final production-ready video file. |
Short-Video-AI Pipeline Advanced Features
- Multi-model fallback: Supports both HuggingFace and Fal.ai for video generation.
- Emotional Tone Mapping: Adjusts ElevenLabs voice settings (stability/style) based on the scene's emotional context.
- Custom Consistency Logic: Ensures visual descriptions and voiceovers represent the exact same moment for maximum immersion.
- Automated Project Scoping: Dynamically calculates video duration and scene count to fit social media platform limits.
SKILL.md
Loading
Related Openclaw Skills
Claw Relay CLI Client
A stateless CLI client that allows AI agents to control real, authenticated remote browsers through simple execution commands.
Tech Solution Research
A professional technical research skill that orchestrates multi-source evidence for framework selection and technology comparison.
Pixel Asset Pipeline
An AI-driven sprite generation and processing workflow designed to turn text prompts into engine-ready pixel art assets for Godot within the Openclaw Skills ecosystem.
Prospect Researcher
An advanced AI research agent that builds structured B2B prospect profiles, identifies key decision-makers, and generates personalized engagement recommendations.
Vaporwave Art Generator
An AI-powered creative tool for generating retro-aesthetic, synthwave, and vaporwave images using simple text prompts.
Kimi K2.5 Vision Integration
A dedicated vision skill that brings Kimi K2.5 image recognition capabilities to Alibaba DashScope GLM users within the OpenClaw ecosystem.
Featured*
