Model Context Protocol

FreeAudioToText MCP Server

Give your AI agents the power of highly accurate audio transcription. Perfect for processing meeting recordings, podcasts, and voice notes directly within Claude and other MCP-compatible clients.

View GitHub Source Get API Key

Why use the FreeAudioToText MCP Server?

Context-Aware Workflows

Allow Claude to transcribe audio files and immediately use the resulting text to answer questions, draft summaries, or extract action items without you ever leaving the chat interface.

Local & Private

The MCP server runs locally on your machine. Audio files are processed securely and deleted immediately. We respect your privacy and never train on your data.

Diarization Ready

Automatically distinguishes between multiple speakers (e.g. SPK_1, SPK_2) making it ideal for processing multi-person interviews and team meetings.

Installation & Setup

The FreeAudioToText MCP Server requires an active API key from our Speech-to-Text API.

1. Install the server

npm install -g @double2/freeaudiototext-mcp

2. Configure your MCP Client (e.g., Claude Desktop)

Add the following configuration to your claude_desktop_config.json file:

{
  "mcpServers": {
    "freeaudiototext": {
      "command": "npx",
      "args": ["-y", "@double2/freeaudiototext-mcp"],
      "env": {
        "FAT_API_KEY": "fat-xxxxxxxxxxxxxxxxxxxxxxxx"
      }
    }
  }
}

3. Restart your Client

Restart Claude Desktop. You should now see the audio transcription tools available in your interface.

Available Tools

transcribe_audio

Transcribe Audio File

Transcribes a local audio or video file into text. Supports MP3, MP4, WAV, and M4A formats. Returns the full transcript.

check_balance

Check Balance

Check your remaining API credits to ensure you have enough balance for your next transcription.