Automatically uploads generated audio files to Amazon S3 with organized directory structure for easy access and sharing
Voice Generation MCP Server
A Model Context Protocol (MCP) server that provides voice generation capabilities using the Minimax AI API. This server converts text to speech and automatically uploads the generated audio files to Amazon S3 for easy access and sharing.
Features
- Text-to-Speech Generation: Convert text to high-quality speech using Minimax AI's voice synthesis API
- S3 Integration: Automatically upload generated audio files to Amazon S3 with organized directory structure
- MCP Protocol Support: Full compatibility with Model Context Protocol for seamless integration with AI assistants
- Authentication: Built-in API key authentication for secure access
- Multiple Transport Modes: Support for HTTP, SSE, and STDIO transport protocols
- Docker Support: Easy deployment with Docker and Docker Compose
- Configurable Audio Settings: Customizable sample rate, bitrate, and format options
Prerequisites
- Python 3.8 or higher
- Minimax AI API credentials
- Amazon S3 bucket and credentials
- (Optional) Docker and Docker Compose for containerized deployment
Installation
Local Installation
- Clone the repository
- Create a virtual environment
- Install dependencies
- Configure environment variables
Docker Installation
- Build the Docker image
- Run with Docker Compose
Configuration
Environment Variables
Create a .env
file based on env.example
with the following required variables:
Voice Generation API (Required)
S3 Configuration (Required)
Usage
Starting the Server
Local Development
Docker
Docker Compose
MCP Clients
The server supports multiple transport modes:
- HTTP:
http://localhost:8000/mcp
- SSE:
http://localhost:8000/sse
- STDIO: Direct process communication
Available Tools
generate_voice
Converts text to speech and uploads to S3.
Parameters:
text
(string, required): The text to convert to speechmodel
(string, optional): Model to use (default: "speech-2.5-hd-preview")voice_id
(string, optional): Voice ID to use (default: "mylxsw_voice_1")speed
(float, optional): Speech speed (default: 1.0, typically 0.5-2.0)
Returns:
- Success message with S3 URL and file size
- Error message if generation fails
Example:
Speed Control:
speed = 0.5
: Half speed (slower speech)speed = 1.0
: Normal speed (default)speed = 1.5
: 1.5x speed (faster speech)speed = 2.0
: Double speed (very fast speech)
License
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Enables text-to-speech conversion using Minimax AI's voice synthesis API with automatic upload to Amazon S3. Supports customizable voice settings including model selection, voice ID, and speech speed control.