sora-video

Generate AI video clips from text prompts via AceDataCloud's OpenAI Sora API.

13|1|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/AceDataCloud/Skills --skill sora-video
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sora-video
Source: https://github.com/AceDataCloud/Skills/tree/main/skills/sora-video
Command: npx skills add https://github.com/AceDataCloud/Skills --skill sora-video

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of generating high-quality AI video by letting you submit text prompts and optional image or character references to the OpenAI Sora API through AceDataCloud.

Core Features & Use Cases

  • Text-to-Video: Turn a detailed description into a short cinematic clip for concepts, storytelling, and ideation.
  • Image-to-Video: Guide motion and scene transformation using a reference image URL for consistent visual direction.
  • Character-Driven Video: Reuse a character extracted from an existing video by specifying start/end timestamps to place them into a new scene.
  • Quality Control: Choose between sora-2 and sora-2-pro, and set duration (including up to 25s with sora-2-pro), size, and orientation to match your production needs.

Quick Start

Generate a 10–15 second landscape video from a text prompt by sending a POST request to the Sora videos endpoint with your prompt, model, and callback URL for results.

Frequently Asked Questions about sora-video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI video from text prompts using the Sora API?

Generate AI video from text prompts by sending a POST request to the Sora videos endpoint with your prompt, model choice, and a callback URL. You can specify parameters like duration, size, and orientation to match your production needs.

Can I use a reference image to guide AI video generation?

Yes, you can guide AI video generation using a reference image URL. This image-to-video feature helps direct motion and scene transformation to maintain consistent visual direction throughout the clip.

How do I put a specific character from an existing video into a new scene?

To place a character into a new scene, use the character-driven generation feature by extracting the character from a source video and specifying start and end timestamps to reuse them in your new generation.

What is the maximum video duration I can create with AI Sora models?

The maximum video duration depends on the model. Using the sora-2-pro model, you can generate AI video clips up to 25 seconds long, while duration parameters can be adjusted for all generation requests.

Do I need an API token to generate text-to-video clips?

Yes, generating text-to-video clips requires ACEDATACLOUD_API_TOKEN authorization. You must include this token when sending requests to the AceDataCloud OpenAI Sora API endpoint.

Which Sora model should I choose for high-quality cinematic video?

Choose between sora-2 and sora-2-pro models for cinematic video generation. The sora-2-pro model supports extended durations up to 25 seconds and offers enhanced quality control for production workflows.