Whisper Speech Recognition MCP Server

@BigUncle

Basic information

About Whisper Speech Recognition MCP Server

A high-performance speech recognition MCP server based on Faster Whisper, providing efficient audio transcription capabilities.

Whisper Speech Recognition MCP Server config

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

{
  "mcpServers": {
    "Fast-Whisper-MCP-Server": {
      "command": "python",
      "args": [
        "whisper_server.py"
      ]
    }
  }
}

Whisper Speech Recognition MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

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

Overview

What is Whisper Speech Recognition MCP Server?

A high-performance speech recognition MCP server based on Faster Whisper, providing efficient audio transcription capabilities. It is designed for developers who want to integrate speech-to-text into AI tools like Claude Desktop.

How to use Whisper Speech Recognition MCP Server?

Install dependencies (Python 3.10+, Faster Whisper, PyTorch, MCP), then run start_server.bat on Windows or python whisper_server.py on other platforms. Configure the server in Claude Desktop by adding its path to claude_desktop_config.json. Three tools are available: get_model_info, transcribe, and batch_transcribe.

Key features of Whisper Speech Recognition MCP Server

Integrated with Faster Whisper for efficient speech recognition
Batch processing acceleration for improved transcription speed
Automatic CUDA acceleration when available
Support for multiple model sizes (tiny to large-v3)
Output formats: VTT subtitles, SRT, and JSON
Model instance caching to avoid repeated loading

Use cases of Whisper Speech Recognition MCP Server

Transcribe a single audio file via the transcribe tool
Batch transcribe all audio files in a folder using batch_transcribe
Integrate speech-to-text capabilities into Claude Desktop
Process long audio files with VAD (Voice Activity Detection) for improved accuracy

Frequently asked questions

What are the runtime dependencies?

Python 3.10+, faster-whisper>=0.9.0, PyTorch and torchaudio (CUDA or CPU version), and mcp[cli]>=1.2.0.

How do I start the Whisper Speech Recognition MCP Server?

On Windows, run `start_server.bat`. On other platforms, run `python whisper_server.py` from the project directory.

How do I integrate the server with Claude Desktop?

Edit `claude_desktop_config.json` (located in `%APPDATA%\Claude` on Windows or `~/Library/Application Support/Claude` on macOS) and add the server configuration with the command `python` and the path to `whisper_server.py`.

What model sizes are supported?

The server supports model sizes from tiny up to large-v3, allowing a trade-off between speed and accuracy.

What output formats are available?

Transcriptions can be produced in VTT (subtitles), SRT (subtitles), or JSON formats.

Comments

More Other MCP servers

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

The Living Bread

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K