sora

Generate and manage short Sora videos via the OpenAI Video API.

Updated Mar 17, 2026
One-click install
npx skills add https://github.com/Estom/aiflex --skill sora-estom
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sora
Source: https://github.com/Estom/aiflex/tree/main/skills-repo/openai-skills/sora
Command: npx skills add https://github.com/Estom/aiflex --skill sora-estom

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Creates and manages short AI-generated videos via OpenAI's Sora models, removing manual complexity around job creation, remixing, polling, and asset downloads so teams can produce product demos, marketing clips, and cinematic shots more efficiently.

Core Features & Use Cases

  • Create new short videos with structured prompt augmentation and sensible defaults (model sora-2, size 1280x720, seconds 4).
  • Remix existing videos while preserving invariants, and poll/download completed assets (video, thumbnail, spritesheet).
  • Batch jobs support via JSONL with concurrency controls and deterministic CLI runs using the bundled scripts/sora.py.
  • Guardrails & validation: enforces allowed models/sizes/durations, input image formats, and content restrictions (no real people, copyrighted characters, or copyrighted music).

Quick Start

Run the bundled Sora CLI with your OPENAI_API_KEY and a concise prompt to create and poll a short video asset.

Frequently Asked Questions about sora

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

FAQPage Schema
How do I generate Sora videos using the OpenAI API?

To generate Sora videos using the OpenAI API, you can run the bundled CLI script with your OPENAI_API_KEY and a text prompt. It creates short videos with sensible defaults like the sora-2 model, 1280x720 size, and 4-second duration.

Can I batch generate Sora videos and poll job status automatically?

Yes, you can batch generate Sora videos by submitting JSONL files with concurrency controls. The CLI workflow automatically polls job status and downloads completed assets like videos, thumbnails, and spritesheets.

Does this Sora CLI support remixing existing videos and reference images?

Yes, the Sora CLI supports remixing existing videos while preserving invariants. You can also provide input reference images to guide the generation of new video assets.

What are the content restrictions when creating videos with OpenAI Sora models?

Content restrictions for OpenAI Sora models prohibit generating real people, copyrighted characters, or copyrighted music. The CLI enforces guardrails and validation for allowed models, sizes, durations, and input image formats.

What's the best way to manage sora-2 and sora-2-pro video generation jobs?

The best way to manage sora-2 and sora-2-pro video generation jobs is using a dedicated CLI workflow. It handles job creation, polling, listing existing jobs, and downloading final assets deterministically.

Why do I need an OPENAI_API_KEY to create Sora videos?

You need an OPENAI_API_KEY to create Sora videos because the CLI sends requests directly to the OpenAI Video API. This key authenticates your access to the sora-2 and sora-2-pro models for generating and remixing assets.