Deepgram Tts MCP Server

@shubhamofbce

Basic information

About Deepgram Tts MCP Server

This server uses deepgram api to generate text to speech and can also play it on your device. You can use this in claude If you prefer listening to audio on claude instead of reading text.

#text-to-speech#deepgram#audio-mcp

Deepgram Tts MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "deepgram-mcp": {
      "command": "/usr/bin/python3",
      "args": [
        "/Users/your-username/path/to/deepgram-mcp/server.py"
      ],
      "env": {
        "DEEPGRAM_API_KEY": "your-deepgram-api-key"
      },
      "description": "Deepgram MCP server to transcribe audio. It is a STT server that uses the Deepgram API to transcribe audio."
    }
  }
}

Deepgram Tts MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Deepgram Tts Mcp?

Deepgram Tts Mcp is an MCP (Model Context Protocol) server that integrates with Claude Desktop to provide real‑time audio generation from text input. It leverages the Deepgram API for text‑to‑speech processing and plays back the generated audio within MCP‑compatible clients like Claude Desktop or Cursor.

How to use Deepgram Tts Mcp?

Clone the repository, install dependencies using Poetry or pip, and register the server in Claude Desktop’s developer settings by editing the configuration JSON with the absolute path to server.py and your Deepgram API key. After saving, restart Claude Desktop and trigger the MCP client to hear audio generated from your text input.

Key features of Deepgram Tts Mcp

Converts text to audio using the Deepgram API
Plays audio in real‑time
Easy to configure and run locally
Integrates with Claude Desktop and other MCP clients
Requires Python 3.13 or higher and a Deepgram API key

Use cases of Deepgram Tts Mcp

Generating spoken responses from text within Claude Desktop
Adding voice output to any MCP‑compatible application
Assisting users who prefer audio over reading text
Rapid prototyping of text‑to‑speech in local development workflows

Frequently asked questions

What prerequisites are needed to run Deepgram Tts Mcp?

You need Python 3.13 or higher, a Deepgram API key (obtainable from the Deepgram developer portal), and an MCP‑compatible client such as Claude Desktop or Cursor.

How do I install the dependencies?

Use Poetry (`poetry install`) or manually install from the `requirements.txt` file with `pip install -r requirements.txt`.

How do I configure the server in Claude Desktop?

Open Claude Desktop → Settings → Developer Settings → Edit Config. Under `mcpServers`, add a `deepgram-mcp` entry with the command set to your Python interpreter, arguments including the absolute path to `server.py`, and the environment variable `DEEPGRAM_API_KEY` set to your API key.

How can I test that the integration works?

After saving the configuration, restart Claude Desktop. Trigger the MCP client to use the `deepgram‑mcp` server; you should hear audio generated from your text input.

Does the server run locally or require cloud access?

The server runs locally and communicates with the Deepgram cloud API for audio generation. All configuration and dependencies are set up on your machine.

Comments

More Other MCP servers

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.