MCP Server Whisper

@arcaputo3

About MCP Server Whisper

An MCP Server for audio transcription using OpenAI

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-whisper": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Server Whisper?

MCP Server Whisper is a Model Context Protocol (MCP) server for advanced audio transcription and processing using OpenAI's Whisper and GPT‑4o models. It enables AI assistants like Claude to search, transcribe, chat with, and generate audio through a standardized interface.

How to use MCP Server Whisper?

Install by cloning the repository and running uv sync. Configure a .env file with OPENAI_API_KEY and AUDIO_FILES_PATH. Launch with bunx dotenv-cli -- claude for local development or add the server to your Claude Desktop configuration. The server exposes tools such as list_audio_files, transcribe_audio, chat_with_audio, and create_audio.

Key features of MCP Server Whisper

Advanced file searching with regex and metadata filters
Multi‑model transcription (Whisper, GPT‑4o transcribe)
Interactive audio chat with GPT‑4o audio models
Text‑to‑speech with customizable voices and speed
Automatic compression of files over 25 MB
Enhanced transcription with specialized templates

Use cases of MCP Server Whisper

Transcribe the latest audio file with detailed insights
Search and filter audio files by name, size, duration, or date
Batch transcribe multiple files in parallel using native MCP concurrency
Generate text‑to‑speech audio from a script with custom voice and style
Ask conversational questions about audio content using GPT‑4o

FAQ from MCP Server Whisper

What models does MCP Server Whisper support?

It supports whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe for transcription; gpt-4o-audio-preview for audio chat; and gpt-4o-mini-tts for text‑to‑speech.

What are the runtime requirements?

Python 3.10 or later and an OpenAI API key set in the OPENAI_API_KEY environment variable. The recommended package manager is uv.

Where are audio files and outputs stored?

Audio files are read from the path specified in AUDIO_FILES_PATH. Transcriptions, converted files, and generated speech are saved to the same directory.

How are large files handled?

Files larger than 25 MB are automatically compressed to meet OpenAI API limits before processing

Frequently asked questions

What models does MCP Server Whisper support?

It supports `whisper-1`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe` for transcription; `gpt-4o-audio-preview` for audio chat; and `gpt-4o-mini-tts` for text‑to‑speech.

What are the runtime requirements?

Python 3.10 or later and an OpenAI API key set in the `OPENAI_API_KEY` environment variable. The recommended package manager is `uv`.

Where are audio files and outputs stored?

Audio files are read from the path specified in `AUDIO_FILES_PATH`. Transcriptions, converted files, and generated speech are saved to the same directory.