I’ve been trying out a new Skill that turns Markdown content into narrated videos — and it’s surprisingly practical. The workflow is simple.
The biggest advantage is that it doesn’t just generate slides or audio separately — it can directly produce a complete video with synchronized audio.
In other words, the final output is an actual MP4 video with the generated narration already included:
Markdown → Slides + Audio → MP4 Video
You can also modify and build on top of the Skill to fit your own workflow. It is released under the Apache License 2.0, so you can customize, extend, and integrate it into your own projects, as long as you comply with the license requirements, including preserving the required attribution and license notices.
You write your content in Markdown, and the Skill handles the rest:
This is particularly useful for turning technical content into:
The interesting part is that the input remains just Markdown.
That means an AI agent can generate the Markdown first, and the Skill can take it from there.
For example:
## Self-Attention
Self-attention allows each token to
consider other tokens in the sequence...
## Why does it matter?
It enables the model to capture
relationships between distant tokens.
→ slides
→ narration
→ synchronized video
No video editor required.
The Skill is available here:
https://github.com/70v-Yoyo/md2video-audio-skill
If you regularly turn Markdown, documentation, or technical notes into educational content, this is worth trying.