Whissle MCP Server

A Python-based server that provides access to Whissle API endpoints for speech-to-text, diarization, translation, and text summarization.

⚠️ Important Notes

• This server provides access to Whissle API endpoints which may incur costs

• Each tool that makes an API call is marked with a cost warning

• Please follow these guidelines:

  1. Only use tools when explicitly requested by the user

  2. For tools that process audio, consider the length of the audio as it affects costs

  3. Some operations like translation or summarization may have higher costs

  4. Tools without cost warnings in their description are free to use as they only read existing data

Related MCP server: Voice Recorder MCP Server

Prerequisites

• Python 3.8 or higher

• pip (Python package installer)

• A Whissle API authentication token

Installation

1. Clone the repository:

   git clone <repository-url> cd whissle_mcp

2. Create and activate a virtual environment:

   python -m venv venv source venv/bin/activate # On Windows, use: venv\Scripts\activate

3. Install the required packages:

   pip install -e .

4. Set up environment variables: Create a .env file in the project root with the following content:

   WHISSLE_AUTH_TOKEN=insert_auth_token_here # Replace with your actual Whissle API token WHISSLE_MCP_BASE_PATH=/path/to/your/base/directory

   ⚠️ Important: Never commit your actual token to the repository. The .env file is included in .gitignore to prevent accidental commits.

5. Configure Claude Integration: Copy claude_config.example.json to claude_config.json and update the paths:

   { "mcpServers": { "Whissle": { "command": "/path/to/your/venv/bin/python", "args": [ "/path/to/whissle_mcp/server.py" ], "env": { "WHISSLE_AUTH_TOKEN": "insert_auth_token_here" } } } }

   • Replace /path/to/your/venv/bin/python with the actual path to your Python interpreter in the virtual environment

   • Replace /path/to/whissle_mcp/server.py with the actual path to your server.py file

Configuration

Environment Variables

• WHISSLE_AUTH_TOKEN: Your Whissle API authentication token (required)

  • This is a sensitive credential that should never be shared or committed to version control

  • Contact your administrator to obtain a valid token

  • Store it securely in your local .env file

• WHISSLE_MCP_BASE_PATH: Base directory for file operations (optional, defaults to user's Desktop)

Supported Audio Formats

The server supports the following audio formats:

• WAV (.wav)

• MP3 (.mp3)

• OGG (.ogg)

• FLAC (.flac)

• M4A (.m4a)

File Size Limits

• Maximum file size: 25 MB

• Files larger than this limit will be rejected

Available Tools

1. Speech to Text

Convert speech to text using the Whissle API.

2. Speech Diarization

Convert speech to text with speaker identification.

3. Text Translation

Translate text from one language to another.

4. Text Summarization

Summarize text using an LLM model.

5. List ASR Models

List all available ASR models and their capabilities.

Response Format

Speech to Text and Diarization

Translation

Summarization

Error Response

Error Handling

The server includes robust error handling with:

• Automatic retries for HTTP 500 errors

• Detailed error messages for different failure scenarios

• File validation (existence, size, format)

• Authentication checks

Common error types:

• HTTP 500: Server error (with retry mechanism)

• HTTP 413: File too large

• HTTP 415: Unsupported file format

• HTTP 401/403: Authentication error

Running the Server

1. Start the server:

   mcp serve

2. The server will be available at the default MCP port (usually 8000)

Testing

A test script is provided to verify the functionality of all tools:

The test script will:

1. Check for authentication token

2. Test all available tools

3. Provide detailed output of each operation

4. Handle errors gracefully

Support

For issues or questions, please:

1. Check the error messages for specific details

2. Verify your authentication token

3. Ensure your audio files meet the requirements

4. Contact Whissle support for API-related issues

License

[Add your license information here]