katareayush/video-captions — explained in plain English
Analysis updated 2026-05-18
Automatically transcribe and burn styled captions into a video file offline using Claude Code.
Describe a caption style in plain words instead of memorizing command line flags.
Generate a schema aware test data seed script for a database from Claude Code.
| katareayush/video-captions | 100/awesome-machine-learning | adam-s/car-diagnosis | |
|---|---|---|---|
| Stars | 8 | 8 | 8 |
| Language | Python | Python | Python |
| Last pushed | — | 2024-08-07 | — |
| Maintenance | — | Stale | — |
| Setup difficulty | easy | easy | moderate |
| Complexity | 2/5 | 1/5 | 3/5 |
| Audience | developer | developer | researcher |
Figures from each repo's GitHub metadata at analysis time.
First run downloads a roughly 150 MB speech recognition model before working fully offline.
This repository is a small marketplace of two plugins for Claude Code, an AI coding assistant, and it hosts video-captions and seedgen. Both are meant to be installed into Claude Code and then used through plain English requests rather than remembering command line flags. The video-captions plugin lets you hand Claude a video file and simply say something like add captions to it. Claude then transcribes the speech in the video entirely on your own computer, without sending anything to an outside service, and burns properly timed captions directly into the video. You do not have to pick from a fixed list of styles either. You can describe what you want in ordinary words, such as big bold yellow captions at the top, or white text with a thick black outline, and Claude translates that description into the right settings automatically. The first time you use it, it downloads a speech recognition model of about 150 megabytes and installs a couple of tools it depends on, and after that everything runs offline with no API key needed. The second plugin, seedgen, is aimed at developers working on a project with a database. You point Claude at your codebase and run a command called seed, and it reads your actual database structure, whether that is SQL migration files, Prisma, Django, Mongoose, or a Solidity smart contract, and writes a ready to run script that fills your database with realistic test data while respecting your existing rules like required fields, unique values, and foreign key relationships. It can also generate that data to match a specific region or country's naming and formatting conventions without changing your underlying schema. Both plugins require Python 3.9 or newer, and video-captions also needs a version of ffmpeg that supports subtitles, which the plugin can install for you automatically on a Mac. The project is released under the MIT license.
A Claude Code plugin pack that adds offline video captioning and automatic, schema-aware test data generation to any project.
Mainly Python. The stack also includes Python, ffmpeg, faster-whisper.
Licensed under MIT, which allows free use, modification, and commercial use as long as you keep the copyright notice.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
double-check against the repo, no cap.