wesbos

Local SvelteKit app for rendering transcript supercuts

83
14
89% credibility
Found May 26, 2026 at 83 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Supercut Studio is a local web application that helps you create video compilations by searching through your video library for specific words or phrases, then stitching together every matching moment into a shareable video.

How It Works

1
🎬 You want to make a supercut video

You have videos you love and want to create something fun from them.

2
📁 You organize your videos into collections

You create folders on your computer and drop your video files inside them.

3
🎤 You turn speech into searchable text

The app listens to each video and writes down every word with timestamps.

4
🔍 You search for a word or phrase

You type a word or phrase, and the app finds every time it was said across all your videos.

5
You choose your creative adventure
✂️
Classic supercut

Stitch together every moment a word was said into one video

💬
Fake sentence mashup

Pick one clip per word and make them say a sentence they never said

🎵
Songify

Arrange clips into a melody and hear your videos sing

6
🎥 You watch your supercut come together

The app clips together your moments, shows you a preview, and estimates how long your video will be.

🎉 You have your supercut!

Your finished video is saved and ready to download and share with the world.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 83 to 83 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is syntax-supercut-studio?

A local SvelteKit app that turns video and audio into searchable, clip-able content. Drop media into organized folders, transcribe it with xAI's speech-to-text, then build supercuts by searching for words or phrases across transcripts. The app stitches matching clips into polished videos, supports regex patterns for complex searches, and even uses AI to generate regex from plain English descriptions. Beyond basic supercuts, it can create "sentence" mashups that make speakers say things they never did, or "songify" clips into melodies. Everything runs locally with ffmpeg handling the video processing.

Why is it gaining traction?

The AI-assisted regex feature is the real differentiator—describe what you want in plain English and it generates the pattern for you. The ability to make speakers say arbitrary sentences is a novelty that appeals to content creators and editors. Everything stays local, so no cloud uploads or subscription fees, and the job system with polling and cancellation gives you control over long renders.

Who should use this?

Podcasters and video editors who want to quickly find and clip moments from their own content. Content creators making compilation videos or highlight reels. Developers building local-first media workflows who need a customizable tool they can extend.

Verdict

A niche but well-executed tool for media editors and podcasters working with transcripts. The local-first approach and AI-assisted search are compelling, but the 0.8999999761581421% credibility score and modest star count suggest it's still early-stage. Test coverage and documentation are minimal, so expect to dig into the code if something breaks. Worth trying if you have the specific workflow it addresses, but don't expect polished production-ready software yet.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.