HN Showcase
Back to browse
Script Snap – Extract code from videos

Script Snap – Extract code from videos

by liumw1203·Feb 21, 2026·14 points·7 comments
Visit ProjectView on HN

AI Analysis

●●SolidSolve My ProblemSlick

Strips YouTube filler for code—but 'AI summarizer' space is crowded with copycats.

Strengths
  • •Focuses specifically on code extraction vs generic summarization, solving a real friction point
  • •Validates terms against engineering ontologies to catch Whisper hallucinations like 'PyTorch' → 'Pie Torch'
  • •Clean product landing page, clear pricing model, working extraction pipeline
Weaknesses
  • •AI video-to-text category has dozens of tools; no evidence of meaningfully better accuracy than Opus + prompting
  • •High dependency on Whisper quality; hallucinations upstream limit any downstream correction
Target Audience

Content creators, developers, technical educators

Similar To

Descript · Fireflies.ai · Rev.com (API)

Post Description

Hi HN, I'm lmw-lab, the builder behind Script Snap.

The Backstory: I built this out of pure frustration. A while ago, I was trying to figure out a specific configuration for a project, and the only good resource I could find was a 25-minute YouTube video. I had to scrub through endless "smash the like button" intros and sponsor reads just to find a single 5-line JSON payload.

I realized I didn't want an "AI summary" of the video; I just wanted the raw code hidden inside it.

What's different: There are dozens of "YouTube to Text" summarizers out there. Script Snap is different because it is explicitly designed as a technical extraction engine.

It doesn't give you bullet points about how the YouTuber feels. It scans the transcript and on-screen visuals to extract specifically:

Code snippets

Terminal commands

API payloads (JSON/YAML)

Security warnings (like flagging sketchy npm installs)

It strips out the "vibe" and outputs raw, formatted Markdown that you can copy straight into your IDE.

Full disclosure on the launch: Our payment processor (Stripe) flagged us on day one (banks seem to hate AI tools), so I've pivoted to a manual "Concierge Alpha" for onboarding. The extraction engine is fully operational, just doing things the hard way for now.

I'd love to hear your thoughts or harsh feedback on the extraction quality!

Similar Projects