Skip to main content
Glama
Sign In
enesjakozh
Audio Transcriber MCP Server

Audio Transcriber MCP Server

by Ichigo3766
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

OpenAI Speech-to-Text transcriptions MCP Server

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

Installation

Setup

  1. Clone the repository:

git clone https://github.com/Ichigo3766/audio-transcriber-mcp.git
cd audio-transcriber-mcp

  1. Install dependencies:

npm install

  1. Build the server:

npm run build

  1. Set up your OpenAI API key in your environment variables.

  2. Add the server configuration to your environment:

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

Replace /path/to/audio-transcriber-mcp with the actual path where you cloned the repository.

Related MCP server: whisper-telegram-mcp

Features

Tools

  • transcribe_audio - Transcribe audio files using OpenAI's API

    • Takes filepath as a required parameter

    • Optional parameters:

      • save_to_file: Boolean to save transcription to a file

      • language: ISO-639-1 language code (e.g., "en", "es")

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

Available Tools

1 tool
transcribe_audioC

Transcribe an audio file using OpenAI Whisper API

Inputs: filepath (required), language, save_to_file.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.1/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined and singular, making it impossible for an agent to misselect between non-existent alternatives.

    Naming Consistency5/5

    The single tool name follows a clear verb_noun pattern (transcribe_audio), and with only one tool, there is no inconsistency to evaluate. The naming is straightforward and aligns with common conventions.

    Tool Count2/5

    A single tool is too few for a server named 'Audio Transcriber MCP Server', as it suggests a limited scope that may not cover related operations like transcription status checks, file management, or configuration. This minimal set could hinder agent workflows that require more comprehensive functionality.

    Completeness2/5

    The tool set is severely incomplete for audio transcription tasks. While it provides a core transcription function, it lacks essential operations such as listing available transcriptions, retrieving transcription results, handling errors, or managing audio files, which are typical in such domains and could lead to agent failures.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    Appeared in Searches