Submit

All Voice Lab MCP

@allvoicelab

Official AllVoiceLab Model Context Protocol (MCP) server, supporting interaction with powerful text-to-speech and video translation APIs. Enables MCP clients like Claude Desktop, Cursor, Windsurf, OpenAI Agents to generate speech, translate videos, and perform intelligent voice conversion. Serves scenarios such as short drama localization for global markets, AI-Generated audiobooks, AI-Powered production of film/TV narration.
Overview

What is AllVoiceLab MCP?

AllVoiceLab MCP is a service that provides voice synthesis and voice conversion functionality. It is fully compatible with the MCP (Model Control Protocol), enabling seamless integration with intelligent assistants that support this protocol.

How to use AllVoiceLab MCP?

To use AllVoiceLab MCP, you need to obtain an API key from AllVoiceLab, then install and configure the service using uv (Python package manager). You can integrate the service through Claude Desktop or in MCP clients such as Cline.

Key features of AllVoiceLab MCP?

  • Provides multiple core API interfaces, including getting supported voice models, available voices, text-to-speech, and voice conversion functionality.
  • Supports multiple languages, including Chinese, English, Japanese, French, German, and Korean.
  • Supports integration with intelligent assistants compatible with the MCP protocol.
  • Provides advanced voice synthesis parameters such as speech rate adjustment.
  • Offers long text translation capabilities for processing extensive content across supported languages.
  • Features subtitle extraction technology to identify and process text from video content.

Use cases of AllVoiceLab MCP?

  • Converting text to natural and fluent speech.
  • Using different voice models and voices for speech synthesis.
  • Performing voice conversion, transforming one voice into another.
  • Adding natural voice capabilities to intelligent assistants, virtual characters, or applications.
  • Translating long-form content between multiple languages while maintaining context and meaning.
  • Extracting and processing subtitles from video content for translation or accessibility purposes.

FAQ from AllVoiceLab MCP?

  • What is the MCP protocol?

MCP (Model Control Protocol) is a standard used for integrating various services and tools in a unified way. More detailed information can be found in the official MCP documentation.

  • Is there a fee for using the AllVoiceLab API?

Using the AllVoiceLab API may require payment. For specific pricing details, please check the AllVoiceLab official website.

  • How to solve problems in API usage?

You can refer to the official documentation or community forums for troubleshooting tips, or check the log records in the project for more detailed error information.

  • Which languages are supported?

AllVoiceLab MCP supports multiple languages, including Chinese (zh), English (en), Japanese (ja), French (fr), German (de), and Korean (ko).

Server Config

{
  "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."
      }
    }
  }
}
© 2025 MCP.so. All rights reserved.

Build with ShipAny.