The AllVoiceLab MCP server allows you to integrate powerful text-to-speech and video translation capabilities into MCP clients like Claude Desktop, Cursor, and Windsurf. This server enables speech generation, video translation, voice conversion, and more through a simple interface.
uv
(Python package manager):
curl -LsSf https://astral.sh/uv/install.sh | sh
The server address must match the region of your API key:
Region | API Key Source | API Domain |
---|---|---|
Global | AllVoiceLab Global | https://api.allvoicelab.com |
Mainland | AllVoiceLab China | https://api.allvoicelab.cn |
{
"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"
}
}
}
}
Note for Windows users: Enable "Developer Mode" in Claude Desktop by clicking "Help" in the top-left menu and selecting "Enable Developer Mode".
Method | Description |
---|---|
text_to_speech | Convert text to speech |
speech_to_speech | Convert audio to another voice while preserving content |
isolate_human_voice | Extract clean human voice by removing background noise |
clone_voice | Create a custom voice profile from an audio sample |
remove_subtitle | Remove hardcoded subtitles from videos |
video_translation_dubbing | Translate and dub video speech into different languages |
text_translation | Translate text files into other languages |
subtitle_extraction | Extract subtitles from videos using OCR |
Ask your MCP client: "Convert 'At All Voice Lab, we're reshaping the future of audio workflows with AI-powered solutions, making authentic voices accessible to creators everywhere.' into voice."
After generating audio from text-to-speech, select the audio file and ask: "Convert this to a male voice."
Select an audio file with mixed sounds and ask: "Remove the background noise."
Select an audio file with a single voice and ask: "Clone this voice."
Select a video file and ask: "Translate this video to Japanese."
Select a video with subtitles and ask: "Remove the subtitles from this video."
Select a long text and ask: "Translate this text to Japanese." (If no language is specified, it will translate to English by default)
Select a video with subtitles and ask: "Extract the subtitles from this video."
Logs can be found at:
For assistance, contact [email protected] with your log files.
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "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."}}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"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."
}
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"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."
}
}
}
}
3. Restart Claude Desktop for the changes to take effect