# audio-transcription-mcp

> Use this tool when you need to transcribe audio files with accurate speaker identification and timestamping. It solves problems such as converting MP3/WAV files to text, identifying speakers, and generating summaries and action items. The tool takes audio files as input and outputs markdown text with speaker labels, timestamps, summaries, and action items.

Canonical page: https://skillsregistry.net/skills/ebmarquez-audio-transcription-mcp  
JSON: https://api.skillsregistry.net/v1/skills/ebmarquez-audio-transcription-mcp

## Description

MCP server for audio transcription with speaker diarization. Transcribes MP3/WAV files using Faster-Whisper and pyannote.audio, outputs markdown with speaker labels, timestamps, summaries, and action items.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/a4fr28ypyw)
- **Repository:** <https://github.com/ebmarquez/audio-transcription-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": "ebmarquez-audio-transcription-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ebmarquez-audio-transcription-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ebmarquez-audio-transcription-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