drio
Open app

Whisper Speech Recognition MCP Server

Source

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

Catalog onlyCatalog onlySTDIO

Overview

Fast-Whisper-MCP-Server is a high-performance speech recognition server based on Faster Whisper, designed to provide efficient audio transcription capabilities.

To use the server, clone the repository, install the required dependencies, and start the server using the provided scripts. You can then configure it with compatible applications like Claude Desktop.

  • Integrated with Faster Whisper for efficient speech recognition - Batch processing acceleration for improved transcription speed - Automatic CUDA acceleration if available - Support for multiple model sizes (tiny to large-v3) - Output formats include VTT subtitles, SRT, and JSON - Model instance caching to avoid repeated loading - Dynamic batch size adjustment based on GPU memory
  1. Transcribing audio files for content creation
  2. Real-time speech recognition for applications
  3. Batch processing of multiple audio files for analysis

Add to your AI client

Use these steps to connect Whisper Speech Recognition MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "fast-whisper-mcp-server-biguncle": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fast-whisper-mcp-server-biguncle"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "fast-whisper-mcp-server-biguncle": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fast-whisper-mcp-server-biguncle"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "fast-whisper-mcp-server-biguncle": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fast-whisper-mcp-server-biguncle"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "fast-whisper-mcp-server-biguncle": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fast-whisper-mcp-server-biguncle"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "fast-whisper-mcp-server-biguncle": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fast-whisper-mcp-server-biguncle"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "fast-whisper-mcp-server-biguncle": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fast-whisper-mcp-server-biguncle"
      ]
    }
  }
}

FAQ

What are the system requirements?

Requires Python 3.10+, Faster Whisper, and PyTorch with CUDA support for optimal performance.

Can it handle multiple audio files at once?

Yes! It supports batch transcription of audio files in a folder.

Is there a GUI available?

Currently, it is command-line based, but it can be integrated with GUI applications like Claude Desktop.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":3834,"uuid":"f12edf79-0991-44e3-8ca2-63efab50b20d","name":"Fast-Whisper-MCP-Server","title":"Whisper Speech Recognition MCP Server","description":"A high-performance speech recognition MCP server based on Faster Whisper, providing efficient audio transcription capabilities.","avatar_url":"https://avatars.githubusercontent.com/u/9360607?v=4","created_at":"$D2025-03-21T22:40:22.108Z","updated_at":"$D2025-03-21T22:58:46.799Z","status":"created","author_name":"BigUncle","author_avatar_url":"https://avatars.githubusercontent.com/u/9360607?v=4","tags":"[]","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/BigUncle/Fast-Whisper-MCP-Server","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":"{\"star\":\"0\",\"license\":\"\",\"language\":\"Python\",\"is_official\":false,\"latest_commit_time\":\"2025-03-22 13:40:58\"}","user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data