OpenAI Speech-to-Text transcriptions

A MCP server that provides audio transcription capabilities using OpenAI's Whisper API

javascript

9

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "ichigo3766-audio-transcriber-mcp": {
      "command": "node",
      "args": [
        "/path/to/audio-transcriber-mcp/build/index.js"
      ],
      "env": {
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY"
      }
    }
  }
}

This MCP server provides audio transcription by leveraging OpenAI's Speech-to-Text capabilities. You can run it locally as a process that your MCP client can connect to, enabling automated transcription of audio files through a simple toolchain.

How to use

You interact with this MCP server through an MCP client to transcribe audio files. Use the provided tool to send an audio file path and receive the transcription text. Optional parameters let you save the transcription to a file and specify the language of the audio for more accurate results.

Key tool you will use: transcribe_audio — Transcribe audio files using OpenAI's API. You provide a filepath as a required parameter. Optional parameters include save_to_file to save the transcription and language to indicate the audio language via an ISO-639-1 code (for example, en for English, es for Spanish). You can chain this with other MCP tools or scripts in your workflow to automate transcription tasks.

How to install

Prerequisites: you need Node.js and npm installed on your system.

Install Node.js and npm if they are not already installed.
Clone the project repository and navigate into it.
Install dependencies.
Build the server.
Set your OpenAI API key in your environment variables.
Add the MCP server configuration to your environment file. The example below shows how to wire up the server so your MCP system can start it with Node.

Additional sections

Configuration details are provided below. Ensure you replace placeholders with your actual values and paths.

MCP server configuration (example) — stdio (local) runtime.

{
  "mcpServers": {
    "audio_transcriber": {
      "command": "node",
      "args": [
        "/path/to/audio-transcriber-mcp/build/index.js"
      ],
      "env": {
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
        "OPENAI_BASE_URL": "",
        "OPENAI_MODEL": ""
      }
    }
  }
}

Available tools

transcribe_audio

Transcribe audio files using OpenAI's API. Requires a filepath and supports optional parameters to save output to file and set the language via an ISO-639-1 code.