Convert VTT subtitle transcripts into clean plain text or markdown.
npx skills add https://github.com/kendreaditya/.config --skill clean-kendreaditya
Please help me install this Agent Skill. Skill: clean Source: https://github.com/kendreaditya/.config/tree/main/claude/skills/clean Command: npx skills add https://github.com/kendreaditya/.config --skill clean-kendreaditya
Clean noisy, machine-generated subtitle text into readable transcripts for easier consumption and sharing.
Run vtt2txt input.vtt to convert a VTT file to plain text.
High-intent search queries and answers about installing and using this skill.
To convert VTT files to plain text or markdown, use the vtt2txt command to process single or batch inputs, stripping headers, timestamps, and cue IDs while deduplicating repeated lines into clean, readable text.
VTT transcripts have repeated lines and broken sentences because machine-generated subtitles often duplicate cues and split fragments across timestamps. Text-cleaning tools stitch these fragments into coherent sentences by deduplicating repeated lines.
Yes, you can batch process multiple VTT files into clean transcripts. The tool applies to batch VTT inputs, producing plain text or markdown outputs with optional metadata for each file in the processing queue.
No, you do not need to install Python dependencies to clean subtitle text. The tool is implemented in Python using the standard library, providing a robust, dependency-free environment for converting VTT files.
The best way to remove timestamps and metadata from VTT files is to use a dedicated text-cleaning script that strips VTT headers, cue IDs, and metadata automatically, leaving only the readable transcript content.
Yes, you can include optional metadata when converting VTT to markdown. The tool outputs plain text or markdown with optional metadata, making it suitable for generating transcripts, summaries, or documentation.
ethan-rioExtract structured summaries and cleaned transcripts from YouTube videos.
ASRagabExport coding agent sessions to Markdown, JSON, HTML, and plain text.
theandyalvarez7-rubyAnalyze text files and directories to produce statistics and transformed outputs.
canvascodingFetch YouTube video transcripts from a video ID or URL.
