vtt-reducer

Convert WebVTT transcripts into consolidated Markdown with timestamps.

2|2|Updated Jan 20, 2026
One-click install
npx skills add https://github.com/srulyt/srulys-agent-packs --skill vtt-reducer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vtt-reducer
Source: https://github.com/srulyt/srulys-agent-packs/tree/main/agent-packs/spec-creator/.roo/skills/vtt-reducer
Command: npx skills add https://github.com/srulyt/srulys-agent-packs --skill vtt-reducer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill streamlines the process of converting verbose WebVTT transcript files into a clean, consolidated Markdown format, making them easily usable as context for AI agents.

Core Features & Use Cases

  • VTT to Markdown Conversion: Transforms raw VTT files into readable Markdown.
  • Speaker Consolidation: Merges consecutive dialogue from the same speaker.
  • Metadata Stripping: Removes VTT-specific cues and identifiers.
  • Use Case: You have a long meeting transcript in VTT format and need to feed it to an AI to summarize or generate action items. This Skill cleans it up first.

Quick Start

Use the vtt-reducer skill to convert the file named 'meeting_transcript.vtt' into a markdown file.

Frequently Asked Questions about vtt-reducer

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

FAQPage Schema
How do I convert VTT meeting transcripts to Markdown for AI summarization?

To convert VTT meeting transcripts to Markdown, this tool parses WebVTT cues, strips metadata, and consolidates speaker dialogue to produce clean text optimized for AI agent context. It transforms verbose files into readable Markdown format for easier language model consumption.

Can I merge consecutive dialogue from the same speaker in WebVTT files?

Yes, you can merge consecutive dialogue from the same speaker in WebVTT files. The tool consolidates repeated speaker entries and removes VTT-specific cues and identifiers, creating a streamlined Markdown document that preserves timestamps for agentic workflows.

Do I need Python 3.6+ to parse VTT files into Markdown?

Yes, you need Python 3.6+ to parse VTT files into Markdown. The tool requires this environment to efficiently process VTT cues, strip metadata, and consolidate speaker dialogue into a clean format suitable for language models.

What is the best way to clean verbose WebVTT files for language models?

The best way to clean verbose WebVTT files for language models is to reduce them into a consolidated Markdown format. This approach removes VTT-specific cues and identifiers while merging consecutive speaker dialogue, making the transcript easily usable as AI context.

How do I generate meeting notes from VTT transcripts for agent context?

To generate meeting notes from VTT transcripts for agent context, the tool reduces raw WebVTT files into clean Markdown. It strips metadata and consolidates speaker dialogue, allowing you to feed the prepared text to an AI to summarize or generate action items.

Does converting VTT to Markdown preserve timestamps for agentic workflows?

Yes, converting VTT to Markdown preserves timestamps for agentic workflows. The tool processes VTT cues to consolidate speaker dialogue while retaining the temporal markers, ensuring the resulting Markdown remains traceable for downstream language model analysis.