Snapdown

The Mac-only caveat I’d want to know before recommending this to my team: when you capture from a browser window, does it pull the rendered text from the DOM or does it run the OCR pipeline on the screenshot? For Notion and Coda docs specifically, the difference shows up in whether nested blocks and toggles come out flat or preserve their structure.

Yeah Broden! Markdown era is here and you're a doing an amazing job on it. Congrats on this impressive launch

Hey Product Hunt 👋

I’m Broden, and I built Snapdown because I kept needing to copy things that were visible on my screen but weren’t actually selectable, like tables, documentation, error messages, and slides.

Most OCR tools recover the words but lose the structure. Headings become ordinary lines, lists turn into paragraphs, and tables become difficult to use. I wanted output I could paste directly into a note, document, issue, or LLM chat without rebuilding it first. That’s why Snapdown produces structured Markdown.

Privacy was also a must for me. Everything runs locally on Apple silicon, so your screenshots stay on your Mac and Snapdown works offline.

I spent a lot of time making the capture loop as fast as possible, while still producing accurate, useful results. The goal is to press a shortcut, select a region, and get your Markdown without interrupting your flow.

Two tips that usually improve the output:
• Instead of capturing a whole screen, split it into smaller, natural sections and combine them with Aggregate Mode. This reduces noise and improves accuracy.
• Zoom in before capturing dense text, tables, or formulas. Clearer source pixels give Snapdown more detail to work with.

I’d love to hear your feedback and feature requests. I’m looking forward to improving Snapdown based on how people actually use it.

Thanks for checking it out!