home / mcp / allvoicelab mcp server

AllVoiceLab MCP Server

Official AllVoiceLab Model Context Protocol (MCP) server, supporting interaction with powerful text-to-speech and video translation APIs.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "allvoicelab-allvoicelab-mcp": {
      "command": "uvx",
      "args": [
        "allvoicelab-mcp"
      ],
      "env": {
        "ALLVOICELAB_API_KEY": "<insert-your-api-key-here>",
        "ALLVOICELAB_BASE_PATH": "optional, default is user home directory. This stores output files.",
        "ALLVOICELAB_API_DOMAIN": "<insert-api-domain-here>"
      }
    }
  }
}

You can use AllVoiceLab MCP Server to generate speech, translate videos, and perform intelligent voice conversions across multiple engines. This MCP server lets clients like Claude Desktop and Cursor access powerful TTS, dubbing, translation, and voice cloning capabilities in a streamlined workflow.

How to use

Connect your MCP client to the AllVoiceLab MCP Server to access text-to-speech, voice conversion, video translation and more. You will typically provide an API key and regional domain, then run the MCP server locally or connect to a remote endpoint through your client.

How to install

Prerequisites you need before starting:

- A valid AllVoiceLab API key.

- The uv Python package manager installed on your system.

Follow these steps to install and start the MCP server.

Install and run the MCP server with uvx

1) Get your API key from AllVoiceLab.
2) Install uv (Python package manager):
   curl -LsSf https://astral.sh/uv/install.sh | sh
3) Configure the MCP server in Claude Desktop or Cursor as shown below. Ensure the API key and domain match your region:

Claude Desktop configuration example

{
  "mcpServers": {
    "AllVoiceLab": {
      "command": "uvx",
      "args": ["allvoicelab-mcp"],
      "env": {
        "ALLVOICELAB_API_KEY": "<insert-your-api-key-here>",
        "ALLVOICELAB_API_DOMAIN": "<insert-api-domain-here>",
        "ALLVOICELAB_BASE_PATH":"optional, default is user home directory.This is uesd to store the output files."
      }
    }
  }
}

Cursor

In Cursor, open Preferences > Cursor Settings > MCP and add the above MCP server configuration as a new global MCP Server.

What you can do after setup

Your MCP client can now interact with AllVoiceLab to perform text-to-speech, voice conversion, voice cloning, video translation and other supported actions.

Additional notes

- The server supports multiple engines and languages, enabling you to generate natural-sounding speech in 30+ languages and perform real-time voice changes. - Your region keys and domains must match exactly to avoid tool unavailability errors. - If you run into issues, check the log files for troubleshooting details.

Troubleshooting

Logs can be found at: - Windows: C:\Users\<Username>\.mcp\allvoicelab_mcp.log - macOS: ~/.mcp/allvoicelab_mcp.log If you encounter problems, contact tech support with your log files for faster resolution. REPOSITORY SLUG: allvoicelab/allvoicelab-mcp

Available tools

text_to_speech

Convert text to speech with AI voices across supported languages.

speech_to_speech

Change the voice of existing speech while preserving the spoken content.

clone_voice

Create a custom voice profile by cloning from an audio sample.

remove_subtitle

Remove hard subtitles from a video using OCR.

video_translation_dubbing

Translate and dub video speech into different languages.

text_translation

Translate text between languages.

subtitle_extraction

Extract subtitles from a video using OCR and output an SRT file.