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)
veed-ugc
Generate UGC-style promotional videos with AI lip-sync. Takes an image (person with product from Morpheus/Ad-Ready) and a script (pure dialogue), creates a video of the person speaking. Uses ElevenLabs for voice synthesis.
ugc-manual
Generate lip-sync video from image + user's own audio recording. ✅ USE WHEN: - User provides their OWN audio file (voice recording) - Want to sync image to specific audio/voice - User recorded the script themselves - Need exact audio timing preserved ❌ DON'T USE WHEN: - User provides text script (not audio) → use veed-ugc - Need AI to generate the voice → use veed-ugc - Don't have audio file yet → use veed-ugc with script INPUT: Image + audio file (user's recording) OUTPUT: MP4 video with lip-sync to provided audio KEY DIFFERENCE: veed-ugc = script → AI voice → video ugc-manual = user audio → video (no voice generation)
ad-ready
Generate advertising images automatically from a product URL + brand profile. ✅ USE WHEN: - User provides a product URL (e-commerce link) - Want automated product scraping + image generation - Have a brand profile to apply (70+ brands available) - Need funnel-stage targeting (awareness/consideration/conversion) - Want AI to auto-select model, scene, lighting based on brand ❌ DON'T USE WHEN: - User provides local product image file → use morpheus-fashion-design - Don't need a person in the image → use nano-banana-pro - Want manual control over model, scene, packs → use morpheus-fashion-design - Already have hero image, need variations → use multishot-ugc - Need video output → use veed-ugc after image generation INPUT: Product URL + brand name (optional) + funnel stage (optional) OUTPUT: PNG advertising image with product + model
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)