Voicepeak

MCP server for VOICEPEAK text-to-speech synthesis

typescript

5

GitHub Stars

typescript

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "k2wanko-voicepeak-mcp": {
      "command": "npx",
      "args": [
        "voicepeak-mcp@latest"
      ]
    }
  }
}

You can run a VoicePeak MCP Server to create and manage VoicePeak text-to-speech tasks from MCP clients. This server lets you synthesize speech, play audio, and list narrators and emotions, using VoicePeak capabilities directly from your MCP workflow.

How to use

To use this MCP server, start it locally and connect an MCP client to send requests for speech synthesis and playback. You can generate audio from text, play audio files, and query available narrators and emotions. If you need custom pronunciation, you can manage a pronunciation dictionary (with Windows limitations noted below). Ensure you have a VoicePeak installation and a compatible MCP client set up to communicate with the server.

How to install

Prerequisites: Install Node.js (which provides npm) so you can run NPX commands. If you prefer an alternative runtime, you can use Bunx, which runs the same MCP server.

Install using NPX (recommended):

npx voicepeak-mcp@latest

Or install using Bunx:

bunx voicepeak-mcp

Configuration

Add the MCP server to your VoicePeak client configuration so it can be discovered and used by MCP workflows.

{
  "mcpServers": {
    "voicepeak": {
      "command": "npx",
      "args": ["voicepeak-mcp@latest"]
    }
  }
}

Platform support and notes

Supported platforms include macOS with full functionality. Windows is partially supported; synthesis and playback work, but pronunciation dictionary features are unavailable. Linux support is planned for the future.

Note: If you need to customize pronunciations on Windows, you must manage the pronunciation dictionary through the VoicePeak application.

Contributing

Contributions through issues and pull requests are welcome. If you run into problems or have improvements, feel free to share them with the project maintainers.

Available tools

synthesize

Generates an audio file from text with optional narrator, emotion, speed, and pitch parameters.

synthesize_and_play

Generates speech from text and plays the result immediately.

play

Plays a provided audio file.

list_narrators

Lists available VoicePeak narrators.

list_emotions

Lists available narrator emotions.

dictionary_list

Lists all pronunciation dictionary entries.

dictionary_add

Adds or updates a pronunciation dictionary entry with surface, pronunciation, and priority.

dictionary_remove

Removes a pronunciation dictionary entry.

dictionary_find

Finds a dictionary entry by text.

dictionary_clear

Clears all dictionary entries.