sora
Generate videos using OpenAI's Sora API. Use when the user asks to generate, create, or make videos from text prompts or reference images. Supports image-to-video generation with automatic resizing.
Why use this skill?
Use the OpenClaw Sora skill to generate professional AI videos from text and images. Fast, automated, and supports multiple resolutions and model types.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/pauldelavallaz/sora-video-genWhat This Skill Does
The Sora video generation skill empowers the OpenClaw AI agent to create high-quality, cinematic video content directly from text-based instructions or existing reference images. By leveraging the advanced OpenAI Sora API, this tool allows for the seamless creation of short-form video content, ranging from 4 to 12 seconds in duration, with support for various aspect ratios and professional-grade resolutions. Whether you are building brand assets, prototyping visual concepts, or generating social media content, this skill automates the entire rendering pipeline, from prompt processing to final file delivery.
Installation
To integrate this functionality into your environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/pauldelavallaz/sora-video-gen
Ensure you have your OPENAI_API_KEY set as an environment variable, or have it ready to pass via the --api-key flag during execution to authenticate with the OpenAI platform.
Use Cases
This skill is perfect for marketers looking to create quick lifestyle commercial snippets, designers needing to visualize motion in a scene, and content creators aiming to generate b-roll for longer projects. You can use it to turn static product photography into engaging "cinematic" product reveals, or to generate abstract atmospheric footage by simply describing the lighting, mood, and camera movement you desire.
Example Prompts
- "Create a 12-second video of a bustling Tokyo street at night, focusing on neon lights reflecting on wet pavement, using the sora-2-pro model."
- "Take this image (reference.png) and turn it into an 8-second video where the clouds move slowly in the background and the lighting changes to sunset."
- "Generate a short video clip showing a slow dolly shot of a luxury watch, highlighting the metallic reflections and premium craftsmanship."
Tips & Limitations
To get the best results, structure your prompts to include specific camera movements (e.g., pan, zoom, tracking shot), lighting conditions, and atmospheric details. Remember that the system will automatically resize your input images to match the target resolution, so expect some cropping if aspect ratios differ significantly. Be mindful that video generation is a resource-intensive process that typically takes between 1 to 3 minutes. Finally, please download your generated files promptly, as the output storage is ephemeral and videos will expire from the cache after approximately one hour.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-pauldelavallaz-sora-video-gen": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, external-api, code-execution
Related Skills
morpheus-fashion-design
Generate professional advertising images with AI models holding/wearing products. ✅ USE WHEN: - Need a person/model in the image WITH a product - Creating fashion ads, product campaigns, commercial photography - Want consistent model face across multiple shots - Need professional lighting/camera simulation - Input: product image + model reference (or catalog) ❌ DON'T USE WHEN: - Just editing/modifying an existing image → use nano-banana-pro - Product-only shot without a person → use nano-banana-pro - Already have the hero image, need variations → use multishot-ugc - Need video, not image → use veed-ugc after generating image - URL-based product fetch with brand profile → use ad-ready instead OUTPUT: Single high-quality PNG image (2K-4K resolution)
brand-analyzer
Analyze brands to generate comprehensive brand identity profiles (JSON). Use when the user wants to analyze a brand, create a brand profile, or needs brand data for ad generation. Stores profiles for reuse across Ad-Ready, Morpheus, and other creative workflows. Can list existing profiles and update them.
ugc-campaign-pipeline
Complete UGC video campaign pipeline: product → hero image → variations → videos → edited final. ✅ USE WHEN: - User says "crear campaña UGC" or "pipeline completo" - Need end-to-end UGC video production - Starting from product image/URL → final edited video - Want the full Doritos-style workflow ❌ DON'T USE WHEN: - Just need one step (use individual skills) - Already have final videos, just editing → use Remotion - Only need images, no video → use Morpheus only OUTPUT: Edited MP4 video with multiple scenes + subtitles + logo
nano-banana-pro
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
sora
Generate videos from text prompts or reference images using OpenAI Sora. ✅ USE WHEN: - Need AI-generated video from text description - Want image-to-video (animate a still image) - Creating cinematic/artistic video content - Need motion/animation without lip-sync ❌ DON'T USE WHEN: - Need lip-sync (person speaking) → use veed-ugc or ugc-manual - Just need image generation → use nano-banana-pro or morpheus - Editing existing videos → use Remotion - Need UGC-style talking head → use veed-ugc INPUT: Text prompt + optional reference image OUTPUT: MP4 video (various resolutions/durations)