md-to-video

Convert markdown scripts into narrated MP4 videos with AI-generated slides and voice-overs.

1|Updated Apr 13, 2026
One-click install
npx skills add https://github.com/cnbison/lbc-skills --skill md-to-video
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: md-to-video
Source: https://github.com/cnbison/lbc-skills/tree/main/skills/md-to-video
Command: npx skills add https://github.com/cnbison/lbc-skills --skill md-to-video

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires mofa-slides, fm_tts, ffmpeg, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the process of turning Markdown scripts into fully narrated videos, saving creators and educators time and effort in producing multimedia presentations.

Core Features & Use Cases

  • Markdown Parsing and Planning: Analyzes scripts to generate slide and narration plans tailored to content structure.
  • AI-Generated Slides: Utilizes mofa-slides to create styled visual presentations based on prompts derived from markdown content.
  • Text-to-Speech Narration: Uses fm_tts to produce voice-overs for each slide, facilitating professional-quality voice narration automatically.
  • Video Assembly: Combines slides and narration into seamless MP4 videos using ffmpeg, suitable for educational, marketing, or training purposes.
  • Use Case: Creators can input a markdown outline of a lecture or tutorial and receive a professional video ready for upload.

Quick Start

Provide a markdown script describing your content, then trigger the skill to generate a complete narrated video suitable for online sharing.

Frequently Asked Questions about md-to-video

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

FAQPage Schema
How do I convert markdown to narrated video automatically?

You need mofa-slides, fm_tts, and ffmpeg installed to execute the full markdown to video workflow. These dependencies handle AI slide generation, text-to-speech narration, and video assembly respectively.

How does automated markdown video generation work for tutorials?

Automated markdown video generation works by parsing markdown scripts to plan content, creating visual slides with mofa-slides, producing audio with fm_tts, and combining them into a seamless multimedia presentation using ffmpeg.

Can I use AI slides and TTS to create multimedia presentations from text?

Yes, ffmpeg is required to assemble markdown scripts into MP4 videos. It combines the AI-generated slides and text-to-speech narration into the final seamless video output.

What is the best way to create training videos from markdown outlines?

Yes, the skill is designed for educators, content creators, and marketers to produce multimedia training or lecture videos quickly without manual video editing.