How do I install the whisper windows mcp server?

Use a recorded configuration for your client, replace example credential values and paths, and verify the documented runtime. Restart or reconnect the client, then inspect the available tools.

What credentials does it need?

It reads `WHISPER_CLI_PATH`, `WHISPER_MODEL`, `WHISPER_SERVER_PATH`, `FFMPEG_PATH` from the environment. Store these in your client's env block or a secrets manager — never commit them to a repository — and grant the narrowest scope that still covers your use case.

SSyncDev

Start a project

Whisper Windows MCP Server

Windows-native MCP server for local audio transcription using whisper.cpp with Vulkan GPU acceleration

Local serverstdioGo

What is the Whisper Windows MCP Server?

Windows-native MCP server for local audio transcription using whisper.cpp with Vulkan GPU acceleration

The short version

A Windows-native MCP (Model Context Protocol) server that lets Claude Desktop transcribe audio and video files locally using whisper.cpp — with GPU acceleration, multilingual support, and batch processing. All transcription runs locally — no audio, video, or file paths ever leave your machine.

What it needs from you

Node.js 18 or later — nodejs.org 2. whisper.cpp binaries with Vulkan GPU support — see Step 1 3. A Whisper model file — see Step 2 4. FFmpeg — required for video files and non-WAV/MP3 audio ---

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

Tool	What it does
transcribe_audio
check_progress
start_batch
check_batch_progress
generate_subtitles
analyze_media
check_config
list_models
download_model
switch_model
check_system
whisper_server

How to install the Whisper Windows MCP Server

{
  "mcpServers": {
    "whisper": {
      "command": "npx",
      "args": [
        "-y",
        "whisper-windows-mcp"
      ],
      "env": {
        "WHISPER_CLI_PATH": "C:\\whisper\\Release\\whisper-cli.exe",
        "WHISPER_MODEL": "C:\\whisper\\models\\ggml-medium.en.bin"
      }
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.

Configuration

Node.js 18 or later — nodejs.org 2. whisper.cpp binaries with Vulkan GPU support — see Step 1 3. A Whisper model file — see Step 2 4. FFmpeg — required for video files and non-WAV/MP3 audio ---

Variable	Description	Required
WHISPER_CLI_PATH	Declared in the maintainer’s client configuration.	Yes
WHISPER_MODEL	Declared in the maintainer’s client configuration.	Yes

Example prompts to try

“Use Whisper Windows MCP to transcribe audio.”
“Use Whisper Windows MCP to check progress.”
“Use Whisper Windows MCP to start batch.”

Frequently asked questions

Windows-native MCP server for local audio transcription using whisper.cpp with Vulkan GPU acceleration Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.