MCP.so
Sign In

TTS MCP

@leo9iota

About TTS MCP

Text-to-Speech MCP Server for IDEs

Basic information

Category

Other

License

MIT

Runtime

go

Transports

stdio

Publisher

leo9iota

Submitted by

leo9iota

Config

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

{
  "mcpServers": {
    "tts-mcp": {
      "command": "/absolute/path/to/extracted/tts-mcp",
      "args": [],
      "env": {
        "FISH_AUDIO_API_KEY": "<OPTIONAL_KEY>",
        "ELEVENLABS_API_KEY": "<OPTIONAL_KEY>"
      }
    }
  }
}

Tools

No tools detected

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

Overview

What is TTS MCP?

TTS MCP is an MCP server that provides Text-to-Speech capabilities. It accepts text output from LLMs, synthesizes it using remote or local audio providers, and plays it directly through the host system's native speakers.

How to use TTS MCP?

Download the pre-compiled binary for your OS from the Releases page, or build from source with Go 1.22+ via just init. Configure API keys in a .env file located in your standard OS configuration directory (e.g., ~/.config/tts-mcp/.env on Linux) using either the tts-mcp-config CLI or manual editing. Then attach the server as a command-line MCP tool in your preferred AI editor, such as Claude Desktop, Cursor, or Antigravity.

Key features of TTS MCP

  • Direct playback of synthesized audio through host system speakers.
  • Aggregates multiple TTS providers into individual command tools.
  • Persona routing maps voices and providers to semantic names.
  • Caches generated audio artifacts locally to an XDG cache directory.

Use cases of TTS MCP

  • Giving spoken voice output to LLM responses in AI editors.
  • Routing text output to specific TTS voices and providers using semantic personas.
  • Offline replay of generated audio through local cache.

FAQ from TTS MCP

Which TTS providers are supported?

FishAudio, ElevenLabs, Neets AI, PlayHT, Cartesia, OpenAI, Azure, and Local APIs.

What are the runtime or build dependencies?

Building from source requires Go 1.22+. Pre-compiled binaries are available for Windows, Linux, and macOS.

Where is the configuration file stored?

The .env file is placed in the standard OS configuration directory: %APPDATA%\tts-mcp (Windows), ~/.config/tts-mcp (Linux), or ~/Library/Application Support/tts-mcp (macOS).

How are cached audio files stored?

Cached audio artifacts are saved locally to an XDG cache directory.

Is there a CLI tool to set up configuration?

Yes, the tts-mcp-config CLI tool can safely initialize the .env file.

Comments

More Other MCP servers