fishaudio-mcp

[](https://mseep.ai/app/cengsin-fishaudio-mcp) # Fish Audio Python MCP Server This is a text-to-speech MCP server implemented using the Fish Audio API. Through this service, you can convert text into natural human voices, supporting various configuration options. ## Features - Basic Text-to-Speech: Convert any text into natural human voices - Advanced Text-to-Speech: Supports custom audio formats, bitrates, and other parameters - MCP Protocol Compatible: Seamlessly integrates with MCP-enabled applications ## Installation ```bash pip install -r requirements.txt ``` Or use a Python package manager to install: ```bash pip install fish-audio-sdk mcp python-dotenv ``` ## Configuration Create a `.env` file in the project root directory with the following content: ``` API_KEY=your_fish_audio_api_key MODEL_ID=your_fish_audio_model_id ``` You need to replace it with your Fish Audio API key and model ID. ## Usage ### Start the service ```bash python app.py ``` Or use the MCP CLI tool: ```bash mcp run --file app.py ``` ### Run the example ```bash python example.py ``` ### Call the service using the MCP client ```python # Example code from mcp.client import MCPClient client = MCPClient("subprocess://python app.py") result = client.call("text_to_speech", {"text": "你好，世界！"}) print(result) # Print the generated audio file path ``` ## API Functionality Description ### text_to_speech Basic text-to-speech function. Parameters: - `text`: The text to convert to speech - `output_path` (optional): Output file path. If not provided, a temporary file will be created. Returns: The path to the generated audio file ### advanced_text_to_speech Advanced text-to-speech function, supporting more configuration options. Parameters: - `text`: The text to convert to speech - `output_path` (optional): Output file path. If not provided, a temporary file will be created. - `format`: Output audio format (mp3, wav, pcm), defaults to mp3 - `mp3_bitrate`: MP3 bitrate (64, 128, 192 kbps), defaults to 128 - `chunk_length`: Chunk length (100-300), defaults to 200 - `normalize`: Whether to normalize the text, defaults to True - `latency`: Latency mode (normal, balanced), defaults to normal Returns: The path to the generated audio file ### get_model_info Get the model information currently in use. Returns: A dictionary containing the model ID and API key prefix ### get_available_models Get a list of available Fish Audio models. Returns: A list of available model information ## License MIT