MCP Server Whisper

🚀 MCP Server Whisper

MCP Server Whisper is a powerful tool designed to achieve efficient audio processing and transcription tasks through standardized protocols and advanced technologies.

🚀 Quick Start

Get started with MCP Server Whisper by following the steps below.

📦 Installation

Install with pip

pip install mcp-server-whisper

📚 Documentation

System Requirements

• Python 3.10 or higher
• Node.js (Recommended v16.24.0 or higher)
• Omi Screen Recorder (Mac only)

Install Dependencies

npm install --save-exact \
  asyncio \
  fast-mcp \
  mcp-server-whisper \
  openai \
  pydub \
  ruff \
  mypy

💻 Usage Examples

Basic Usage

from mcp_server_whisper import start

# Start MCP Server Whisper with default configuration
start()

# Or specify a custom audio file path
AUDIO_FILES_PATH = "/path/to/your/audio/files"
start(audio_files_path=AUDIO_FILES_PATH)

📚 Documentation

MCP Server Configuration

Configure by creating a mcp_server_whisper_config.json file:

{
  "servers": {
    "whisper": {
      "host": "localhost",
      "port": 3001,
      "workers": 4,
      "max_body_size": "5mb"
    }
  },
  "openai": {
    "api_key": "your_openai_api_key",
    "model": "gpt-4o-transcribe",
    "temperature": 0.7
  }
}

🔧 Technical Details

Toolchain

The project uses modern Python development tools:

# Run tests
pytest

# Tests with coverage
pytest --cov=src

# Format code
ruff format src

# Check code style
ruff check src

# Run type checking (strict mode)
mypy --strict src

Key Components

• MCP Protocol: Exposes audio processing capabilities through a standardized MCP tool interface.
• Parallel Processing: Uses asyncio and batch processing to improve performance.
• File Management: Implements detection, verification, conversion, and compression of audio files.
• Rich Transcription: Provides high-quality transcription with different OpenAI models (including gpt-4o-transcribe).
• Optimized Performance: Built-in caching mechanism to speed up repetitive operations.

🤝 Contribution Guidelines

How to Contribute

1. Fork the repository on GitHub.
2. Create a feature branch (git checkout -b feature/amazing-feature).
3. Commit your code changes.
4. Run tests and checks (pytest && ruff check src && mypy --strict src).
5. Commit your changes (git commit -m 'Add some amazing feature').
6. Push to the branch (git push origin feature/amazing-feature).
7. Create a Pull Request.

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

🙏 Acknowledgments

Thanks to the following projects and technologies:

• Model Context Protocol (MCP): Provides the protocol specification.
• pydub: Used for audio processing.
• OpenAI Whisper: Used for audio transcription.
• asyncio: Supports asynchronous programming.
• fast-mcp: A fast MCP implementation.