Minimax MCP JS

🚀 Export Tools

This project provides a set of tools for converting text to audio, images, and videos. It also includes development and configuration guides.

🚀 Quick Start

Installation

npm install

Or use yarn:

yarn install

Start the Development Server

npm run dev

Or use yarn:

yarn dev

Build the Project

npm run build

Or use yarn:

yarn build

✨ Features

Text-to-Audio

Generate audio from text.

• Tool Name: text_to_audio
• Parameters:
  • text: Text content (required).
  • model: Model version, options include 'speech-02-hd', 'speech-02-turbo', 'speech-01-hd', 'speech-01-turbo', 'speech-01-240228', 'speech-01-turbo-240228', default is 'speech-02-hd'.
  • voiceId: Voice ID, default is 'male-qn-qingse'.
  • speed: Speech speed, range from 0.5 to 2.0, default is 1.0.
  • vol: Volume, range from 0.1 to 10.0, default is 1.0.
  • pitch: Pitch, range from -12 to 12, default is 0.
  • emotion: Emotion, options include 'happy', 'sad', 'angry', 'fearful', 'disgusted', 'surprised', 'neutral', default is 'happy'. Note: This parameter only applies to 'speech-02-hd', 'speech-02-turbo', 'speech-01-turbo', 'speech-01-hd' models.
  • format: Audio format, options include 'mp3', 'pcm', 'flac', 'wav', default is 'mp3'.
  • sampleRate: Sampling rate (Hz), options include 8000, 16000, 22050, 24000, 32000, 44100, default is 32000.
  • bitrate: Bitrate (bps), options include 64000, 96000, 128000, 160000, 192000, 224000, 256000, 320000, default is 128000.
  • channel: Audio channel, options include 1 or 2, default is 1.
  • languageBoost: Language enhancement, default is 'auto'.
  • latexRead: Whether to enable formula reading function.
  • pronunciationDict: Pronunciation dictionary.
  • stream: Whether to enable streaming output.
  • subtitleEnable: Whether to enable subtitle generation.
  • outputDirectory: Directory to save the output file (optional).
  • outputFile: Path to save the output file (optional, if not provided, a file name will be automatically generated).

Text-to-Image

Generate an image based on text description.

• Tool Name: text_to_image
• Parameters:
  • prompt: Image description (required).
  • model: Model version, default is 'image-01'.
  • aspectRatio: Aspect ratio, default is '1:1', options include '1:1', '16:9', '4:3', '3:2', '2:3', '3:4', '9:16', '21:9'.
  • n: Number of images to generate, range from 1 to 9, default is 1.
  • promptOptimizer: Whether to optimize the prompt, default is true.
  • subjectReference: Path to the character reference (optional).
  • outputDirectory: Directory to save the output file (optional).

Text-to-Video

Generate a video based on text description.

• Tool Name: text_to_video
• Parameters:
  • prompt: Video description (required).
  • model: Model version, default is 'video-01'.
  • duration: Video duration (seconds), default is 10.
  • outputDirectory: Directory to save the output file (optional).

📦 Project Export

If you need to export this project as a module, please refer to the following code:

// Export the project to other places

🔧 Technical Details

Project Structure

The project consists of the following main components:

• src/: Source code directory.
• public/: Public resource directory.
• package.json: Project dependency management file.
• tsconfig.json: TypeScript configuration file (if using TypeScript).

📚 Configuration

Environment Variables

You can set the following environment variables in package.json:

{
  "config": {
    "PORT": 3000,
    "NODE_ENV": "development"
  }
}

Other Notes

Please ensure that all dependencies are installed and the environment variables are correctly configured.