Whisper MCP Server

A Model Context Protocol (MCP) server for advanced audio transcription and processing using OpenAI's Whisper and GPT-4o models.

Local serverstdioPython

What is the Whisper MCP server?

Most AI and media services work still happens through a UI a human drives. Whisper MCP server moves it into the conversation instead. A Model Context Protocol (MCP) server for advanced audio transcription and processing using OpenAI's Whisper and GPT-4o models.

The short version

MCP Server Whisper provides a standardized way to process audio files through OpenAI's latest transcription and speech services. By implementing the Model Context Protocol, it enables AI assistants like Claude to seamlessly interact with audio processing capabilities.

The tools it exposes

The server publishes 12 tools. What each one is for:

  • min_duration_seconds — 300 (5 minutes)
  • min_modified_time — <timestamp for Jan 1, 2024>
  • sort_by — "size"
  • voice — "shimmer"
  • model — "gpt-4o-mini-tts" (default high-quality model)
  • instructions — "Speak in an enthusiastic, podcast host style" (optional)
  • speed — 1.0 (default, can be adjusted)
  • Type — Safe Responses**: Every tool returns a strongly-typed Pydantic model (TranscriptionResult, ChatResult, AudioProcessingResult, TTSResult)
  • Single — Item Operations**: One call processes one file, with MCP protocol handling parallelism natively
  • Per — File Error Handling**: Failures are isolated to individual operations, not entire batches
  • Self-Documenting — Type hints provide autocomplete and validation in IDEs and AI models
  • Transcription — The Transcription tool exposed by this server

What it needs from you

Configuration is passed through the environment: OPENAI_API_KEY, AUDIO_FILES_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

How it compares

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Whisper's toolset — min_duration_seconds, min_modified_time, sort_by and 9 more — is a fair guide to whether it matches your workflow. It is maintained by arcaputo3; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Whisper.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
min_duration_seconds300 (5 minutes)
min_modified_time<timestamp for Jan 1, 2024>
sort_by"size"
voice"shimmer"
model"gpt-4o-mini-tts" (default high-quality model)
instructions"Speak in an enthusiastic, podcast host style" (optional)
speed1.0 (default, can be adjusted)
TypeSafe Responses**: Every tool returns a strongly-typed Pydantic model (TranscriptionResult, ChatResult, AudioProcessingResult, TTSResult)
SingleItem Operations**: One call processes one file, with MCP protocol handling parallelism natively
PerFile Error Handling**: Failures are isolated to individual operations, not entire batches
Self-DocumentingType hints provide autocomplete and validation in IDEs and AI models
TranscriptionThe Transcription tool exposed by this server.

How to install the Whisper MCP server

{
  "mcpServers": {
    "whisper": {
      "command": "uvx",
      "args": ["mcp-server-whisper"],
      "env": {
        "OPENAI_API_KEY": "your_openai_api_key",
        "AUDIO_FILES_PATH": "/path/to/your/audio/files"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
OPENAI_API_KEYCredential the server authenticates with.Yes
AUDIO_FILES_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Whisper to min duration seconds.
  • Use Whisper to min modified time.
  • Use Whisper to sort by.

Frequently asked questions

It connects Whisper to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (min_duration_seconds, min_modified_time, sort_by, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Whisper directly.