text_to_audioLABSCO SUMMARY
Speech, a cloned voice, an image or a video, produced from inside the conversation.
Video generation is asynchronous — the generate call starts the job and a separate query call collects it — so it is worth telling your client the completion rule up front rather than having it wait on the first response.
What it is
The official MiniMax MCP server, connecting an MCP client to MiniMax's text-to-speech and image and video generation APIs. It runs over stdio locally, or SSE when deployed to a server.
What you get
text_to_audio— convert text to audio with a given voicelist_voices— list every voice available to your accountvoice_clone— clone a voice from audio files you supplyvoice_design— generate a voice from a descriptive prompt, with preview texttext_to_image— generate an image from a promptgenerate_video— generate video from a prompt, including the MiniMax-Hailuo-02 model with 6s and 10s durations and 768P or 1080P outputquery_video_generation— poll a video generation task for its result, which is how the asynchronous path is driven
Requirements
uv installed, then run it with uvx minimax-mcp. Two environment variables must agree: MINIMAX_API_KEY and MINIMAX_API_HOST, where the global host is https://api.minimax.io and the mainland host is https://api.minimaxi.com. A key from one region against the other's host returns an invalid-API-key error, which is the most common setup failure. MINIMAX_MCP_BASE_PATH sets where generated files land locally, and MINIMAX_API_RESOURCE_MODE chooses between a returned URL and a local download. On Windows, Claude Desktop needs Developer Mode enabled. Calls to these tools consume MiniMax credits.
Setup effort
One command plus a key — uvx minimax-mcp -y, then supply credentials
USE CASES
01
Narrating something you just wrote
List the voices available to your account, pick one, and convert the text to audio in the same turn.
02
Keeping one consistent voice across a project
Clone a voice from reference audio once, then use it for every subsequent narration instead of re-picking a stock voice.
03
Inventing a voice that does not exist yet
Describe the voice you want and get it generated, with preview text so you can hear it before committing.
04
Producing a short video from a prompt
Start the generation, then poll for the result — MiniMax-Hailuo-02 takes duration and resolution options.
05
Getting an illustration without leaving the chat
Generate the image from a prompt and have it saved to your configured local output directory rather than returned only as a URL.
7 tools
Listed in project docs. Your client may show a different list.
list_voicesvoice_clonegenerate_videotext_to_imagequery_video_generationvoice_designBEFORE YOU INSTALL
What to know first
Tools you get
7 tools named in the project's documentation.
Requires
- uvx on PATH
- MINIMAX_API_KEY in your environment
- MINIMAX_API_HOST in your environment
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx minimax-mcp -yMCP Clients
Claude Desktop, Cursor
JSON
{
"mcpServers": {
"MiniMax": {
"command": "uvx",
"args": [
"minimax-mcp",
"-y"
],
"env": {
"MINIMAX_API_KEY": "<YOUR_MINIMAX_API_KEY>",
"MINIMAX_MCP_BASE_PATH": "<YOUR_MINIMAX_MCP_BASE_PATH>",
"MINIMAX_API_HOST": "https://api.minimax.io",
"MINIMAX_API_RESOURCE_MODE": "url"
}
}
}
}
