generate_video
Generate a video based on text prompts.
Note: This tool calls MiniMax API and may incur costs. Use only when explicitly requested by the user.
LABSCO SUMMARY
Draft assets land as files instead of as links to a console.
Speech, images, video and music sit behind one connection, and each generator writes into a directory you pass rather than handing back a URL to collect later. Long renders do not have to block: video generation can run asynchronously and return a task you poll. The costs are real per call, so the tools are worth wiring where a person asks for an asset rather than where a model might decide one would help.
What it is
MiniMax's generation APIs behind ten tools: text to speech with voice, emotion and speed control, voice cloning and voice design, text to image, text or image to video, music generation, and local playback.
What you get
- Text spoken in a chosen voice with emotion, speed, pitch, volume, format, bitrate and sample rate, saved to a directory you name
- Subtitles produced alongside the audio when you ask for them
- The available voices listed, when the account is on the host that supports it
- A voice cloned from an audio file you supply, and a new voice designed from a written description, with preview audio
- Images generated from a prompt with aspect ratio, a count, and an optional prompt optimizer
- Video generated from a prompt or from a first-frame image, with duration and resolution, and an async mode whose task you poll by id
- Music generated from a prompt for the style and the lyrics to sing
- WAV and MP3 files played back locally
Requirements
A MiniMax account with an API key in MINIMAX_API_KEY and the matching host in MINIMAX_API_HOST — the international and mainland platforms issue different keys, and a key from one will not authenticate against the other. MINIMAX_MCP_BASE_PATH sets where generated files are written and MINIMAX_RESOURCE_MODE whether they come back as files or URLs. Node with npx. Every generation tool spends credits on the account, which is why their descriptions ask to be called only when the user actually asked for output. MIT.
Setup effort
One command plus a key — npx -y minimax-mcp-js, then supply credentials
USE CASES
01
Giving a script a voice for a rough cut
Pick a voice from the account, set the emotion and speed, and get an audio file on disk you can drop straight into the edit.
02
Matching a narrator you already have
A sample of the existing voice produces a cloned one, which the speech call then uses for everything that follows.
03
Turning a still into a short clip
Video from a first-frame image runs long enough to be worth doing asynchronously — the call returns a task, and the query call collects it.
04
Getting concept art in front of the team
Prompt in, images out, with aspect ratio and count set per call and an optional optimizer on the prompt itself.
05
Inventing a voice that does not exist yet
Describe the voice you want in words, listen to the preview, then use the id it returns for the rest of the script.
06
Scoring a clip with music that has your own words in it
Music generation takes both a prompt for the style and the lyrics to sing, and writes the audio out at the bitrate and sample rate you ask for.
10 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
image_to_video
Generate a video based on an image.
Note: This tool calls MiniMax API and may incur costs. Use only when explicitly requested by the user.
list_voices
List all available voices. Only supported when api_host is https://api.minimax.chat.
music_generation
Create a music generation task using AI models. Generate music from prompt and lyrics.
Note: This tool calls MiniMax API and may incur costs. Use only when explicitly requested by the user.
play_audio
Play an audio file. Supports WAV and MP3 formats. Does not support video.
query_video_generation
Query the status of a video generation task.
text_to_audio
Convert text to audio with a given voice and save the output audio file to a given directory. If no directory is provided, the file will be saved to desktop. If no voice ID is provided, the default voice will be used.
Note: This tool calls MiniMax API and may incur costs. Use only when explicitly requested by the user.
text_to_image
Generate images based on text prompts.
Note: This tool calls MiniMax API and may incur costs. Use only when explicitly requested by the user.
voice_clone
Clone a voice using the provided audio file. New voices will incur costs when first used.
Note: This tool calls MiniMax API and may incur costs. Use only when explicitly requested by the user.
voice_design
Generate a voice based on description prompts.
Note: This tool calls MiniMax API and may incur costs. Use only when explicitly requested by the user.
BEFORE YOU INSTALL
What to know first
Tools you get
10 tools when we connected. The documentation describes 7; image_to_video, list_voices and music_generation also ship but are undocumented.
Requires
- npx on PATH
- MINIMAX_API_KEY in your environment
Where it runs
Both documented clients run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 10 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y minimax-mcp-jsMCP Clients
Claude Desktop, Cursor
JSON
{
"mcpServers": {
"minimax-mcp-js": {
"command": "npx",
"args": [
"-y",
"minimax-mcp-js"
],
"env": {
"MINIMAX_API_HOST": "https://api.minimaxi.chat",
"MINIMAX_API_KEY": "<YOUR_MINIMAX_API_KEY>",
"MINIMAX_MCP_BASE_PATH": "<YOUR_MINIMAX_MCP_BASE_PATH>",
"MINIMAX_RESOURCE_MODE": "url"
}
}
}
}
