Skip to content

Gobbler

Gobby the Turkey mascot

Universal Content Conversion to Markdown for AI

Get Started  |  CLI Reference  |  GitHub


What is Gobbler?

Gobbler transforms any content into clean, structured markdown that AI systems can immediately use:

gobbler youtube "https://youtube.com/watch?v=..." -o transcript.md
gobbler document report.pdf -o report.md
gobbler audio meeting.mp3 -o meeting.md
gobbler webpage "https://docs.example.com" -o docs.md

One tool. One output format. Every content type.


Install in 60 Seconds

# Clone and install
git clone https://github.com/Enablement-Engineering/gobbler.git
cd gobbler && make install

# Try it
gobbler youtube "https://www.youtube.com/watch?v=dQw4w9WgXcQ"

Full installation guide


What Can Gobbler Convert?

Content Command Requirements
YouTube videos gobbler youtube URL None
Audio/video files gobbler audio FILE ffmpeg
PDF, DOCX, PPTX, XLSX gobbler document FILE Docker
Web pages gobbler webpage URL Docker
Browser sessions gobbler browser extract Browser extension

Three Ways to Use Gobbler

Direct command-line usage for humans and scripts:

gobbler youtube "URL" -o transcript.md
gobbler audio recording.mp3 --model medium
gobbler document report.pdf --no-ocr

For Claude Desktop and Claude Code:

claude mcp add gobbler-mcp -- uv --directory /path/to/gobbler run gobbler-mcp

Then ask Claude: "Transcribe this YouTube video: URL"

Markdown instruction files that teach Claude how to use the CLI. Skills provide progressive disclosure—AI only loads what it needs.

Learn about Skills


Pluggable Providers

Swap backends without changing your workflow:

# Use local Whisper (default, free, private)
gobbler audio recording.mp3

# Use OpenAI's API (faster, paid)
gobbler audio recording.mp3 --provider openai-whisper
Category Providers
Transcription whisper-local, openai-whisper
Documents docling
Web Pages crawl4ai

Provider documentation


Output Format

Every conversion produces markdown with YAML frontmatter:

---
source: https://youtube.com/watch?v=VIDEO_ID
type: youtube_transcript
title: "Video Title"
duration: 847
word_count: 2341
---

# Video Title

Content here, ready for AI consumption...

Next Steps