video-translate-pipeline

Convert YouTube VTT subtitles into bilingual Obsidian Markdown notes.

Updated May 1, 2026
One-click install
npx skills add https://github.com/xiaoquqi/hermes-agent-skills --skill video-translate-pipeline
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: video-translate-pipeline
Source: https://github.com/xiaoquqi/hermes-agent-skills/tree/main/productivity/video-translate-pipeline
Command: npx skills add https://github.com/xiaoquqi/hermes-agent-skills --skill video-translate-pipeline

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

YouTube VTT subtitles are transformed into merged semantic paragraphs and bilingual Obsidian notes through an end-to-end automation pipeline.

Core Features & Use Cases

  • VTT to semantic paragraphs: deduplicates and stitches fragments into coherent sections.
  • Bilingual Obsidian export: generates frontmatter-enabled Markdown with bilingual tables.
  • End-to-end automation: orchestrates parsing, translation, and vault formatting.

Quick Start

Run the pipeline to convert a YouTube VTT file into a bilingual Obsidian note.

Frequently Asked Questions about video-translate-pipeline

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert YouTube VTT subtitles into bilingual Obsidian notes?

To convert YouTube VTT subtitles into bilingual Obsidian notes, this pipeline applies an end-to-end automation process that parses the VTT file, deduplicates and stitches fragments into semantic paragraphs, translates the text, and formats it into Markdown with frontmatter and bilingual tables for your Obsidian vault.

What is the best way to automate translation of YouTube video transcripts for note-taking?

Automating translation of YouTube video transcripts is best handled by a pipeline that orchestrates parsing, semantic paragraph merging, translation, and vault formatting, producing translated Markdown notes and updating Obsidian vault indices automatically through Python scripts.

Does the VTT translation pipeline require Python to generate Markdown notes?

Yes, the VTT translation pipeline utilizes Python scripts to produce translated Markdown notes and update Obsidian vault indices, requiring a target environment configured to execute these scripts for the end-to-end automation to function correctly.

Can I use this to deduplicate and stitch VTT subtitle fragments into coherent paragraphs?

Yes, you can use this pipeline to deduplicate and stitch VTT subtitle fragments, transforming fragmented YouTube video transcripts into coherent semantic paragraphs before applying translation and generating the final bilingual Obsidian notes.

What are the limitations when processing YouTube VTT files for Obsidian vault formatting?

The pipeline is specifically designed for YouTube VTT files and depends on a target environment configured for Python scripts, meaning it may not directly process other video subtitle formats or update vaults without the required Obsidian formatting setup.