video-production

Automate narrated educational slide video production with script generation, TTS, and FFmpeg assembly.

98|25|Updated Jul 3, 2026
One-click install
npx skills add https://github.com/speechlab0210/video-production-skill --skill video-production-speechlab0210
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-production
Source: https://github.com/speechlab0210/video-production-skill/tree/main
Command: npx skills add https://github.com/speechlab0210/video-production-skill --skill video-production-speechlab0210

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the end-to-end production of educational slide videos, eliminating the manual labor of script-to-slide generation, voiceover synthesis, and subtitle alignment.

Core Features & Use Cases

  • Automated Pipeline: Orchestrates script writing, slide generation (hand-drawn or HTML), TTS narration, and video assembly.
  • Quality Assurance: Includes mandatory ASR verification for audio-text alignment and visual checks for slide readability.
  • Use Case: An AI agent can take a topic, generate a series of hand-drawn lecture slides, synthesize a professional ElevenLabs voiceover, and output a fully assembled, subtitled MP4 video ready for YouTube.

Quick Start

Read the video-production-skill SKILL.md file and follow the mandatory checklist to produce a video on the topic of your choice.

Frequently Asked Questions about video-production

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

FAQPage Schema
How do I automate educational video production from script to MP4?

Automating educational video production coordinates script generation, slide rendering, TTS synthesis, and FFmpeg assembly. It takes a topic input and outputs a fully assembled, subtitled MP4 ready for publishing.

Can I use ElevenLabs TTS for automated lecture video voiceovers?

Yes, ElevenLabs TTS synthesizes professional voiceovers for automated lecture videos. The pipeline integrates ElevenLabs API keys to generate narration, which is verified for alignment before video assembly.

Do I need Node.js and Python to run automated TTS video assembly?

Yes, Node.js, Python, and FFmpeg are required to execute the full automated TTS video assembly pipeline. API keys for ElevenLabs and OpenAI are also needed to generate scripts and synthesize audio.

What is ASR verification in automated slide video generation?

ASR verification in automated slide video generation is a mandatory quality assurance step that checks audio-text alignment. It ensures the synthesized TTS narration matches the script for accurate subtitle synchronization.

Does automated video production support hand-drawn lecture slides?

Yes, automated video production supports generating both hand-drawn and HTML lecture slides. The pipeline orchestrates rendering these slides, adding TTS narration, and assembling them into a final MP4.

Why does my automated TTS video pipeline require OpenAI API keys?

Automated TTS video pipelines require OpenAI API keys to autonomously generate the educational script content. The script dictates slide rendering and provides the text for ElevenLabs voiceover synthesis.