Veed-UGC AI Video Generator for Openclaw

Transform static images of people with products into realistic lip-synced promotional videos using AI.

pauldelavallaz
v1.0.1
Feb 12, 2026
5
2.1k
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install veed-ugc

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 veed-ugc 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 Veed-UGC AI Video Generator?

Veed-UGC is a specialized tool within the Openclaw Skills ecosystem designed to automate the creation of User Generated Content (UGC) videos. It leverages ComfyDeploy workflows and ElevenLabs voice synthesis to animate static images—specifically those featuring a person with a product—into high-quality, lip-synced promotional clips.

This skill is ideal for marketers and developers looking to scale their video production without traditional filming. By integrating seamlessly with other tools like Morpheus or Ad-Ready, Veed-UGC bridges the gap between static design and engaging video content. It simplifies the complex process of AI video generation into a single command-line execution or API call, making it an essential part of any modern content automation stack for Openclaw Skills users.

Veed-UGC AI Video Generator Use Cases

  • Automated creation of product testimonial videos using synthetic personas.
  • Scaling social media marketing campaigns with localized lip-synced dialogue.
  • Converting static Morpheus or Ad-Ready outputs into dynamic video ads.
  • Rapid prototyping of video content for A/B testing promotional scripts.

How Veed-UGC AI Video Generator Works

  1. The user provides a source image (ideally a person holding a product) and a text-based dialogue script.
  2. The skill sends these inputs to a specialized ComfyDeploy workflow hosted via API.
  3. ElevenLabs generates a voiceover using a specified Voice ID based on the provided script.
  4. The AI model processes the image and audio to animate the person's mouth and facial expressions with natural movement.
  5. A final MP4 video file is generated and saved to the specified output path.

Veed-UGC AI Video Generator Setup

To get started with this skill in your Openclaw Skills environment, ensure you have the necessary dependencies and API keys configured.

# Navigate to the skills directory
cd ~/.clawdbot/skills/veed-ugc

# Run the generation script with your image and script
uv run scripts/generate.py \
  --image "https://example.com/product-image.png" \
  --script "This product is a game changer! You have to try it." \
  --output "ugc-video.mp4"

Ensure your ComfyDeploy and ElevenLabs credentials are set in your environment variables.

Veed-UGC AI Video Generator Data Schema & Taxonomy

The skill handles input and output data using a structured format to ensure compatibility with other Openclaw Skills.

Field Type Description
image String URL or local path to the source JPG/PNG image.
script String Pure dialogue text (no stage directions allowed).
voice_id String ElevenLabs unique identifier for the AI voice.
output String File path for the resulting .mp4 video.

Veed-UGC AI Video Generator Advanced Features

  • Multi-platform integration with Morpheus and Ad-Ready for end-to-end automated ad generation.
  • Support for custom ElevenLabs Voice IDs to match specific brand personas.
  • High-precision lip-syncing that accommodates various languages and accents within Openclaw Skills workflows.
  • CLI-based automation for batch processing large volumes of promotional scripts.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*