M

MiniMax

Installable
minimaxai
GitHub

About

Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation, video generation, and music generation APIs. This server allows MCP clients like Claude Desktop, Cursor, Windsurf, and others to generate speech, clone voices, generate video, generate images, and more.

Features

  • Text to Audio: Convert text to audio with a variety of available voices
  • Voice Cloning: Clone voices using provided audio files
  • Voice Design: Generate custom voices from descriptive prompts with preview audio
  • Video Generation: Generate videos from prompts using MiniMax-Hailuo-02 model with duration (6s/10s) and resolution (768P/1080P) controls
  • Image Generation: Generate images from text prompts
  • Music Generation: Create music tracks from prompts and lyrics using music-1.5 model
  • Query Video Status: Query the result of video generation tasks

Available Tools

  • text_to_audio - Convert text to audio with a given voice
  • list_voices - List all voices available
  • voice_clone - Clone a voice using provided audio files
  • voice_design - Generate a voice from a prompt using preview text
  • generate_video - Generate a video from a prompt
  • text_to_image - Generate an image from a prompt
  • query_video_generation - Query the result of video generation task
  • music_generation - Generate a music track from a prompt and lyrics

Configuration

API Keys and Region

⚠️ Important: The API host and key vary by region and must match; otherwise, you'll encounter an Invalid API key error.

Global Region:

Mainland China Region:

Environment Variables

  • MINIMAX_API_KEY: Your MiniMax API key (required)
  • MINIMAX_API_HOST: API host URL based on your region (required)
  • MINIMAX_MCP_BASE_PATH: Local output directory path for downloaded files (optional, e.g., /User/xxx/Desktop)
  • MINIMAX_API_RESOURCE_MODE: Output mode for audio/image/video resources - either url (default) or local (optional)

Transport

Supports two transport types:

  • stdio: Run locally, communication through stdout, supports processing local files or valid URL resources
  • SSE: Can be deployed locally or in cloud, communication through network, recommended to use URL for input when deployed in the cloud

Usage Tips

Video Generation in Async Mode

For video generation, define completion rules before starting. Configure rules in your IDE settings or define them explicitly when making requests.

⚠️ Warning: Using these tools may incur costs based on MiniMax API usage.

Additional Resources

This server runs through your single 1Server connection. No extra config required.

0Installs
1.5KStars

Categories

AI ToolsProductivity

Tags

Official