Resemble

🚀 Voice Generation Server with Resemble AI

The voice generation server powered by Resemble AI can be connected to your project in various ways, including integration with Cursor AI and Claude Desktop. This document will guide you through the setup, operation, and integration processes.

🚀 Quick Start

The voice generation server powered by Resemble AI can be connected to your project through multiple methods, including integration with Cursor AI and Claude Desktop. This document will guide you through the setup, operation, and integration processes.

✨ Features

• Connect to your project in multiple ways.
• Integrate with Cursor AI and Claude Desktop.

📦 Installation

Create a Virtual Environment (Recommended)

To ensure compatibility, create an independent Python environment for this project:

python -m venv mcp-venv
source mcp-venv/bin/activate  # Use `mcp-venv\Scripts\activate` on Windows

Install Dependencies

Install the required packages in the active environment:

pip install uvicorn fastapi python-dotenv requests pydantic httpx sse-starlette
pip install git+https://github.com/modelcontextprotocol/python-sdk.git

📚 Documentation

Configure Environment Variables

Copy and edit the example environment file:

cp .env.example .env

Add your Resemble AI API key to the .env file:

RESEMBLE_API_KEY=your_api_key_here

Optional: Customize audio output settings:

OUTPUT_DIR=./output
AUDIO_FORMAT=mp3

Create the output directory:

mkdir -p output

Run the Server

Use the new CLI tool to run the server, supporting multiple implementation methods:

# Activate your environment (if not already activated)
conda activate resemble-mcp
# Or
source venv/bin/activate

# Use the MCP SDK implementation (recommended)
python -m src.cli --implementation mcp --port 8083

# Other implementations:
# HTTP API implementation
python -m src.cli --implementation http --port 8083
# Direct API implementation
python -m src.cli --implementation direct --port 8083
# Resemble SDK implementation
python -m src.cli --implementation sdk --port 8083

Integrate with Cursor AI

In Cursor, interact with the Resemble AI voice generation server through the SSE interface:

1. Open Cursor's settings -> AI -> MCP Server.
2. Click "Add Server" and enter the SSE URL: http://localhost:8083/sse (adjust the port as needed).

Integrate with Claude Desktop

Configure the MCP server in Claude Desktop: Edit the claudia.json file and add the following content:

{
  "mcpServers": {
    "resemble-ai": {
      "command": "python",
      "args": ["-m", "src.cli", "--implementation", "mcp"],
      "env": {
        "RESEMBLE_API_KEY": "your_api_key_here"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Tool Documentation

list_voices

List all available voice models on Resemble AI.

• Parameters: None
• Returns:
  • voices: A list containing the ID, name, gender, language, accent, and description of the voice models.

generate_tts

Generate voice from text.

• Parameters:
  • text: The text to be converted to voice.
  • voice_id: The ID of the target voice model (obtained from list_voices).
  • output_path: The path to save the generated audio file.
• Returns: The audio file is saved to the specified path.

💻 Usage Examples

Basic Usage - Generate Voice

python -m src.cli generate-tts "This is a test." --voice_id your_voice_id --output_path output/audio.mp3

Basic Usage - List Voices

python -m src.cli list-voices

⚠️ Important Note

1. Python Version Requirement: The MCP package requires Python 3.10 or higher.
2. API Key Security: Ensure the security of your Resemble API key and avoid disclosure.
3. Port Conflict: If port 8083 is occupied, try other ports.

❓ Frequently Asked Questions

Question 1: How to obtain a voice ID?

Use the list_voices command to get a list of available voice models:

python -m src.cli list-voices

Question 2: How to handle audio formats?

Set the output format (e.g., mp3 or wav) in the .env file.

🌟 Conclusion

With this document, you can easily integrate the Resemble AI voice generation server into your project and collaborate seamlessly with Cursor AI and Claude Desktop.