TTS MCP Server

Deep learning for Text to Speech by Coqui.

Local serverstdioPython

What is the TTS MCP server?

TTS MCP server exists for a simple reason — assistants are far more useful when they can act on TTS directly instead of describing what you should do. Deep learning for Text to Speech by Coqui.

What you get

🛠️ Tools for training new models and fine-tuning existing models in any language.

  • High-performance Deep Learning models for Text2Speech tasks
  • Text2Spec models (Tacotron, Tacotron2, Glow-TTS, SpeedySpeech)
  • Speaker Encoder to compute speaker embeddings efficiently
  • Vocoder models (MelGAN, Multiband-MelGAN, GAN-TTS, ParallelWaveGAN, WaveGrad, WaveRNN)
  • Fast and efficient model training
  • Detailed training logs on the terminal and Tensorboard

What the assistant can call

Once TTS is connected, these are the calls the assistant has available:

  • Vocoders — The Vocoders tool exposed by this server

Configuration and credentials

You will need one environment variable: OUTPUT_PATH. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

Installation goes through your MCP client rather than a global install: point it at TTS on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Choosing this one

Among the monitoring and observability options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. TTS's toolset — Vocoders — is a fair guide to whether it matches your workflow. It is maintained by Eren Gölge; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the tts mcp server does with a few real requests.

Available tools

ToolWhat it does
VocodersThe Vocoders tool exposed by this server.

How to install the TTS MCP server

{
  "mcpServers": {
    "tts-1": {
      "command": "uvx",
      "args": ["TTS"],
      "env": {
        "OUTPUT_PATH": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
OUTPUT_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use TTS to Vocoders.

Frequently asked questions

It connects TTS to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (Vocoders) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with TTS directly.