chatgpt-image-short-video

Generates short videos from ChatGPT images with ffmpeg and text-to-speech audio.

Updated May 4, 2026
One-click install
npx skills add https://github.com/ChronoAIProject/nyx-skills --skill chatgpt-image-short-video
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: chatgpt-image-short-video
Source: https://github.com/ChronoAIProject/nyx-skills/tree/main/chatgpt-image-short-video
Command: npx skills add https://github.com/ChronoAIProject/nyx-skills --skill chatgpt-image-short-video

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the need for a streamlined workflow to produce high-quality, short vertical videos, using ChatGPT image generation and a series of local assembly steps, suitable for consistent and reproducible output.

Core Features & Use Cases

  • Image Generation through ChatGPT: Use ChatGPT for creating images as visual components of short videos.
  • Local Narration and Subtitles: Integrate local text-to-speech and subtitle generation to accompany the visual content.
  • Media Pipeline Automation: Automate the creation of video, covers, and a manifest through ffmpeg and PIL for image manipulation.
  • Use Case: If you need a repeatable process for converting script or content into a short vertical video, this Skill could be the tool for you, ensuring the process is consistent from project to project.

Quick Start

Install the skill with 'npx skills add ChronoAIProject/nyx-skills/chatgpt-image-short-video'.

Frequently Asked Questions about chatgpt-image-short-video

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

FAQPage Schema
How do I automate short video production from images using ChatGPT?

You can automate short video production by using ChatGPT for image generation and coordinating local text-to-speech with subtitle creation. The Skill orchestrates these media pipeline tools to assemble professional vertical videos from a script.

What is the best way to add text-to-speech and subtitles to a vertical video?

The best way to add text-to-speech and subtitles is by integrating local narration generation with an automated media pipeline. This Skill coordinates local text-to-speech and subtitle creation alongside ChatGPT-generated images to produce the final video.

Can I use ffmpeg and PIL for image-to-video media pipeline automation?

Yes, you can use ffmpeg and PIL for image-to-video media pipeline automation. This Skill utilizes ffmpeg and PIL to automate the creation of vertical short videos, covers, and manifests, ensuring consistent and reproducible output from project to project.

Do I need a script to generate a professional short video with ChatGPT?

Yes, you need a script to generate a professional short video with ChatGPT. The Skill focuses on converting a script into a short vertical video by combining ChatGPT image generation with local narration and subtitle creation for a consistent output.

Does this image-to-video workflow support local text-to-speech narration?

Yes, this image-to-video workflow supports local text-to-speech narration. It coordinates local narration and subtitle creation with media pipeline tools to accompany ChatGPT-generated visual content, ensuring a reproducible process for vertical videos.

Why use an automated media pipeline for short vertical video creation?

You use an automated media pipeline for short vertical video creation to ensure consistent and reproducible output from project to project. This Skill automates video, covers, and manifests through ffmpeg and PIL, streamlining the assembly of ChatGPT-generated images.