What is Daisys?

Daisys is a platform for generating high-quality text-to-speech (TTS) and text-to-voice (TTV) outputs. The Daisys-MCP server integrates with MCP clients to provide TTS/TTV functionality through a command-line interface.

How to use Daisys-MCP?

1. Get a Daisys Account: Sign up on Daisys.ai and note your email and password.
2. Install Dependencies:
   • macOS: brew install portaudio
   • Linux: sudo apt install portaudio19-dev libjack-dev
3. Configure MCP Client: Add the Daisys-MCP server to your MCP config (e.g., Claude, Cursor, mcp-cli). Specify your Daisys credentials and a storage path for audio files.
4. Optionally Build from Source: Clone the repo, install Python/uV dependencies, and configure the server locally.

Key Features

• High-quality TTS/TTV generation
• Integration with MCP clients (Claude, Cursor, VSCode)
• Cross-platform support (Linux, macOS)
• Customizable storage path for audio files

Use Cases

1. Accessibility: Convert text to speech for screen readers or assistive technologies.
2. Content Creation: Generate voiceovers for videos, podcasts, or audiobooks.
3. Development: Test TTS functionality in applications (e.g., chatbots, IVR systems).

FAQ

• Is Daisys-MCP free?

  The beta version is free, but token costs may apply for full integration tests.

• What platforms are supported?

  Currently macOS and Linux (Windows support may vary).

• How do I debug issues?

  Use uv run pytest or consult the Daisys-MCP GitHub repo.

• Can I self-host?

  Yes, by building from source and running the server locally.

Daisys MCP server

Daisys-mcp is a beta version and doesn't have a stable release yet. But you can try it out by doing the following:

1. Get an account on Daisys and create an username and password.

If you run on mac os run the following command:

brew install portaudio

If you run on linux run the following command:

sudo apt install portaudio19-dev libjack-dev

2. Add the following configuration to the mcp config file in your MCP client (Claude Desktop, Cursor, mcp-cli, mcp-vscode, etc.):

{
  "mcpServers": {
    "daisys-mcp": {
      "command": "uvx",
      "args": ["daisys-mcp"],
      "env": {
        "DAISYS_EMAIL": "{Your Daisys Email}",
        "DAISYS_PASSWORD": "{Your Daisys Password}",
        "DAISYS_BASE_STORAGE_PATH": "{Path where you want to store your audio files}"
      }
    }
  }
}

To build from source:

1. clone the repository: git clone https://github.com/daisys-ai/daisys-mcp.git

2. cd into the repository: cd daisys-mcp

3. Install uv (Python package manager), install with curl -LsSf https://astral.sh/uv/install.sh | sh or see the uv repo for additional install methods.

4. Create a virtual environment and install dependencies using uv:

uv venv
# source .venv/Scripts/activate (Windows)
source .venv/bin/activate (mac and linux)
uv pip install -e .

5. Add the following to your config file in your MCP client (Claude Desktop, Cursor, mcp-cli, mcp-vscode, etc.):

{
    "mcpServers": {
        "daisys-mcp": {
            "command": "uv",
            "args": [
                "--directory",
                "{installation_path}/daisys-mcp",
                "run",
                "-m",
                "daisys_mcp.server"
            ],
            "env": {
                "DAISYS_EMAIL": "{Your Daisys Email}",
                "DAISYS_PASSWORD": "{Your Daisys Password}",
                "DAISYS_BASE_STORAGE_PATH": "{Path where you want to store your audio files}"
            }
        }
    }
}

Common Issues

If you get any issues with portaudio on linux, you can try installing it manually:

sudo apt-get update
sudo apt-get install -y portaudio19-dev

Contributing

If you want to contribute or run from source:

1. Clone the repository:

git clone https://github.com/daisys-ai/daisys-mcp.git
cd daisys_mcp

2. Create a virtual environment and install dependencies using uv:

uv venv
source .venv/bin/activate
uv pip install -e .
uv pip install -e ".[dev]"

3. Copy .env.example to .env and add your DAISYS username and password:

cp .env.example .env
# Edit .env and add your DAISYS username and password

4. Test the server by running the tests:

uv run pytest

you can also run a full integration test with:

uv run pytest -m 'requires_credentials' # ⚠️ Running full integration tests does costs tokens on the Daisys platform 

5. Debug and test locally with MCP Inspector: uv run mcp dev daisys_mcp/server.py