mcp-tts-server
If you are the rightful owner of mcp-tts-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The mcp-tts-server is a Text-to-Speech server utilizing the Model Context Protocol (MCP) and the Groq API for generating lifelike audio from text.
The mcp-tts-server is designed to provide a robust Text-to-Speech (TTS) solution by leveraging the Model Context Protocol (MCP) and the Groq API. This server facilitates the conversion of text into high-quality audio, supporting various audio formats such as wav, mp3, aac, opus, and flac. It integrates seamlessly with the Groq API, which is responsible for the actual speech generation, ensuring that the audio output is both natural and lifelike. The server is built using Bun, a fast JavaScript runtime, and offers a command-line interface for easy deployment and management. Additionally, it includes an optional feature to play the generated audio directly on the server machine using the `@tropicbliss/symphonia` library. The server requires a Groq API key, which must be set as an environment variable, to authenticate and interact with the Groq API.
Features
- Implements an MCP server for TTS functionality.
- Connects to the Groq API for generating lifelike audio from text.
- Provides a `generate_speech` tool accessible via the MCP protocol.
- Supports multiple audio output formats (wav, mp3, aac, opus, flac).
- Uses `@tropicbliss/symphonia` to play the generated audio directly on the server machine (optional).
Tools
generate_speech
Tools for generating voice through the MCP protocol
