mcp-tts-server

by kaichen

AI/Speech TTS Groq API Audio Generation Speech Synthesis

This project is a Text-to-Speech (TTS) server based on the Model Context Protocol (MCP), utilizing the Groq API for speech generation. It allows you to generate lifelike audio from text using the Groq API.

View on GitHub

Last updated: N/A

What is mcp-tts-server?

mcp-tts-server is an MCP server that provides Text-to-Speech functionality by connecting to the Groq API. It allows users to generate audio from text using the generate_speech tool.

How to use mcp-tts-server?

To use the server, you need to install the dependencies using bun install. Then, configure the server in your MCP client configuration file, providing the command to run the server and setting the GROQ_API_KEY environment variable. You can then use the generate_speech tool via the MCP protocol.

Key features of mcp-tts-server

Implements an MCP server for TTS functionality
Connects to the Groq API for speech generation
Provides a generate_speech tool accessible via the MCP protocol
Supports multiple audio output formats (wav, mp3, aac, opus, flac)

Use cases of mcp-tts-server

Generating audiobooks from text
Creating voiceovers for videos
Building interactive voice-based applications
Implementing accessibility features for text content

FAQ from mcp-tts-server

What is the Model Context Protocol (MCP)?

MCP is a protocol for communication between different models and services.

What is the Groq API?

The Groq API is a service that provides access to powerful AI models, including text-to-speech models.

How do I get a Groq API key?

You need to sign up for an account on the Groq platform and obtain an API key from their dashboard.

What audio formats are supported?

The server supports wav, mp3, aac, opus, and flac audio output formats.

Can I play the generated audio directly on the server?

Yes, the server can optionally play the generated audio directly on the server machine using @tropicbliss/symphonia.