# Hermes YouTube Transcript MCP Server

> Use this tool when you need to automatically transcribe YouTube audio into text, solving the problem of manual transcription and enabling easy ingestion into note-taking systems like Obsidian and Hermes. It takes YouTube audio as input and produces Markdown and JSON transcripts as output. Ideal for use cases where local, fast, and private transcription of YouTube content is required.

Canonical page: https://skillsregistry.net/skills/thomkozik-hermes-yt-transcriber-mcp  
JSON: https://api.skillsregistry.net/v1/skills/thomkozik-hermes-yt-transcriber-mcp

## Description

Downloads YouTube audio and transcribes it locally using faster-whisper, saving transcripts as Markdown and JSON files for Obsidian and Hermes ingestion.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** social-media
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/epwgk2h34k)
- **Repository:** <https://github.com/thomkozik/hermes-yt_transcriber-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "thomkozik-hermes-yt-transcriber-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/thomkozik-hermes-yt-transcriber-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/thomkozik-hermes-yt-transcriber-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt
