语音转录服务器

# Model Configuration
DEFAULT_MODEL=mlx-community/whisper-large-v3-turbo
OUTPUT_FORMATS=txt,md,srt,json

# Performance Settings
MAX_WORKERS=4
TEMP_DIR=./temp

# Optional: API Keys for future cloud features
# OPENAI_API_KEY=your_key_here

{
  "mcpServers": {
    "whisper-transcription": {
      "command": "poetry",
      "args": ["run", "python", "src/whisper_mcp_server.py"],
      "cwd": "/absolute/path/to/mcp-whisper-transcription"
    }
  }
}

# Run the MCP server directly
poetry run python src/whisper_mcp_server.py

# Or use the development server
poetry run python -m src.whisper_mcp_server

# Single file transcription
result = await client.call_tool("transcribe_file", {
    "file_path": "interview.mp4",
    "output_formats": "txt,srt",
    "model": "mlx-community/whisper-large-v3-turbo"
})

# Transcription with Voice Activity Detection
result = await client.call_tool("transcribe_file", {
    "file_path": "long_interview.mp4",
    "output_formats": "txt,srt",
    "use_vad": True  # Remove silence for faster processing
})

# Batch processing
result = await client.call_tool("batch_transcribe", {
    "directory": "./podcasts",
    "pattern": "*.mp3",
    "max_workers": 4
})

# Check supported formats
formats = await client.call_tool("get_supported_formats", {})

# Run all tests
poetry run pytest

# Run with coverage
poetry run pytest --cov=src --cov-report=html

# Run specific test file
poetry run pytest tests/test_mcp_tools.py -v

# Format code
poetry run black .
poetry run isort .

# Type checking (optional)
poetry run mypy src/

# Lint code
poetry run flake8 src/

mcp-whisper-transcription/
├── src/
│   └── whisper_mcp_server.py    # Main MCP server
├── tests/                       # Comprehensive test suite
├── examples/                    # Usage examples and test files
├── transcribe_mlx.py           # MLX Whisper integration
├── whisper_utils.py            # Utility functions
└── pyproject.toml              # Project configuration