nijivoice-mcp

# NijiVoice MCP This is an MCP server implementation for the [Nijivoice API](https://nijivoice.com/api) using FastMCP. ## Overview This MCP server provides functionality for performing speech synthesis using the Nijivoice API. The main features are as follows: - Get a list of available Voice Actors - Generate audio files from text - Check credit balance ## Prerequisites - Python 3.12 or higher - [uv](https://github.com/astral-sh/uv) - Fast Python package manager and installer - [fastmcp](https://github.com/jlowin/fastmcp) v2.2.8 or higher - Nijivoice API key ## Installation 1. Clone the repository: ```bash git clone https://github.com/ryoooo/nijivoice-mcp-beta.git cd nijivoice-mcp-beta ``` 2. Create a virtual environment and install dependencies using [uv](https://github.com/astral-sh/uv): ```bash uv venv source .venv/bin/activate # Linux/Mac # or .venv\Scripts\activate # Windows uv pip install -e . ``` 3. Create a `.env` file and set the Nijivoice API key: ``` NIJIVOICE_API_KEY=your_api_key_here ``` ## Usage ### Starting the MCP Server To start the server in development mode: ```bash uv run fastmcp dev server.py ``` To start the server in production mode: ```bash uv run fastmcp run server.py ``` ### Install and Use To install and use the MCP server: ```bash uv run fastmcp install server.py ``` ### Features The following features are available: #### Tools - `get_voice_actors()`: Get a list of available voice actors - `generate_voice(script, actor_id, speed, emotional_level, sound_duration, format)`: Generate voice - `get_credit_balance()`: Get credit balance #### Resources - `voice-actors://list`: Voice actor list resource - `voice-actors://{actor_id}`: Get information for a specific voice actor - `credit://balance`: Credit balance resource #### Prompt - `voice_generation_prompt()`: Provides a prompt for voice generation ## Voice Generation Parameters The following parameters can be specified when generating voice: - `script`: Text to read (maximum 3,000 characters) (required) - `actor_id`: ID of the voice actor to use (defaults to the first voice actor if omitted) - `speed`: Reading speed (0.4 to 3.0, default: 1.0) - `emotional_level`: Emotional level (0.0 to 1.5, default: -1.0 = use voice actor's default setting) - `sound_duration`: Phoneme pronunciation length (0.0 to 1.7, default: -1.0 = use voice actor's default setting) - `format`: Audio format ("mp3" or "wav", default: "mp3") ## Response Format The response format when generating voice is as follows: ```json { "generatedVoice": { "audioFileUrl": "URL for audio playback", "audioFileDownloadUrl": "URL for audio download", "duration": 1312, // Audio length (milliseconds) "remainingCredits": 3613 // Remaining credits after generation } } ``` ## Testing To run tests: ```bash uv run pytest ``` To display detailed test results: ```bash uv run pytest -v ``` To generate a coverage report: ```bash uv run pytest --cov=nijivoice ``` ## License [MIT](LICENSE) ## Acknowledgments - [fastmcp](https://github.com/jlowin/fastmcp) - Python framework for building MCP (Model Context Protocol) servers - [Nijivoice API](https://nijivoice.com/api) - API that provides high-quality speech synthesis