Home / MCP / Nijivoice MCP Server

Nijivoice MCP Server

Provides voice synthesis via Nijivoice API with MCP endpoints to list actors, generate speech, and check credits.

python

1star

View on GitHub

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
    "mcpServers": {
        "nijivoice": {
            "command": "uv",
            "args": [
                "run",
                "fastmcp",
                "dev",
                "server.py"
            ],
            "env": {
                "NIJIVOICE_API_KEY": "YOUR_API_KEY"
            }
        }
    }
}

Nijivoice MCP Server provides an MCP interface to use the Nijivoice API for speech synthesis. You can list available voice actors, generate speech from text, and check your credit balance directly through MCP-compatible clients.

How to use

You run the MCP server locally and connect your MCP client to the server to access three core capabilities: list voice actors, generate speech from text, and check your credits. Use the standard MCP client flow to start the server, call the available endpoints, and handle responses that include playback or download URLs and credit information.

Once the server is running, you can perform these actions through your MCP client: retrieve the list of voice actors, initiate a text-to-speech generation with chosen parameters, and monitor remaining credits after each generation. The server exposes resources for voice actors and credit balance, and it provides a prompt starter for voice generation when you prepare your requests.

How to install

Prerequisites you need before installing this MCP server:

Python 3.12 or newer
uv - fast Python package manager and installer
fastmcp v2.2.8 or newer
NIJIVOICE_API_KEY from Nijivoice API

1. Clone the project repository and enter the folder.

git clone https://github.com/ryoooo/nijivoice-mcp-beta.git
cd nijivoice-mcp-beta

2. Create and activate a Python virtual environment using uv, then install the package in editable mode.

uv venv
source .venv/bin/activate  # Linux/Mac
# or
.venv\Scripts\activate  # Windows

uv pip install -e .

3. Create a configuration file with your Nijivoice API key.

NIJIVOICE_API_KEY=your_api_key_here

4. Start in development mode to test locally.

uv run fastmcp dev server.py

5. Start in production mode once you are ready to deploy.

uv run fastmcp run server.py

6. Install the MCP server for integration in your environment.

uv run fastmcp install server.py

Additional configuration and notes

Environment variable required for API access: NIJIVOICE_API_KEY. Keep this value secret and do not commit it to version control.

Features you can use with the MCP server

Tools include the following functions you call from your MCP client:

- get_voice_actors: Retrieve the list of available voice actors.

- generate_voice: Create speech from text with chosen actor and parameters.

- get_credit_balance: Check the current credit balance.

Available tools

get_voice_actors

Retrieve the list of available voice actors from Nijivoice.

generate_voice

Generate speech from provided text using a selected voice actor and parameters.

get_credit_balance

Check the current remaining credit balance.