n8n-nodes-minimax-unofficial

This is an n8n community node that lets you use MiniMax.io Text-to-Speech API in your n8n workflows.

MiniMax.io provides advanced AI-powered text-to-speech capabilities with high-quality voice synthesis, emotion control, and support for multiple languages.

n8n is a fair-code licensed workflow automation platform.

Installation
Operations
Credentials
Compatibility
Usage
Resources

Installation

Follow the installation guide in the n8n community nodes documentation.

GUI installation

1. Go to Settings > Community Nodes.
2. Select Install.
3. Enter n8n-nodes-minimax-unofficial in Enter npm package name.
4. Agree to the risks of using community nodes: select I understand the risks of installing unverified code from a public source.
5. Select Install.

After installing the node, you can use it like any other node. n8n displays the node in search results in the Nodes panel.

Manual installation

To get started install the package in your n8n root directory:

npm install n8n-nodes-minimax-unofficial

Operations

Text to Speech

• Convert text to high-quality speech using MiniMax's AI models
• Support for multiple voice models (speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo)
• Customizable voice emotions (happy, sad, angry, fearful, disgusted, surprised, neutral)
• Multiple audio formats (MP3, WAV, FLAC, PCM)
• Configurable sample rates and bitrates
• Voice cloning support with custom voice IDs

Credentials

This node requires a MiniMax API account. You can sign up for free at MiniMax.io.

To set up your credentials:

1. Create an account at MiniMax.io
2. Navigate to the API Platform
3. Generate your API key
4. Choose the appropriate API host:
   • Global: https://api.minimaxi.chat (default)
   • China: https://api.minimax.chat

Setting up credentials in n8n:

1. Go to Credentials in n8n
2. Select Create New Credential
3. Choose MiniMax API
4. Enter your API Key
5. Select the appropriate API Host for your region
6. Test the connection
7. Save the credential

Compatibility

• Minimum n8n version: 0.198.0
• Tested with n8n versions: 0.198.0+

Usage

Basic Text-to-Speech

1. Add the MiniMax TTS node to your workflow
2. Connect your MiniMax API credentials
3. Set the Text field with the content you want to convert to speech
4. Choose your preferred Model (speech-02-hd recommended for best quality)
5. Configure additional options as needed:
   • Voice ID: Use system voices or custom cloned voices
   • Emotion: Set the emotional tone of the speech
   • Format: Choose output audio format (MP3, WAV, FLAC, PCM)
   • Sample Rate: Audio quality setting
   • Bitrate: Audio compression setting
   • Channels: Mono or Stereo output

Voice Cloning

To use voice cloning features:

1. First, clone a voice using MiniMax's voice cloning API (outside of n8n)
2. Use the returned voice ID in the Voice ID field
3. The node will use your custom voice for text-to-speech conversion

Advanced Configuration

The node supports all MiniMax TTS API parameters:

• Model Selection: Choose between different quality/speed trade-offs
• Emotion Control: Add emotional expression to speech (works with newer models)
• Audio Quality: Configure sample rate, bitrate, and channels
• Format Options: Multiple output formats for different use cases

Error Handling

The node includes comprehensive error handling:

• API authentication errors
• Invalid parameter validation
• Network timeout handling
• Graceful degradation with "Continue on Fail" option

Example Workflows

Simple Text-to-Speech

Manual Trigger → MiniMax TTS → Save to File

Batch Processing

Read CSV → Split Input → MiniMax TTS → Save to File

Voice Assistant

Webhook → Process Text → MiniMax TTS → Return Audio

Resources

• MiniMax.io Official Website
• MiniMax API Documentation
• n8n Community Nodes Documentation
• n8n Documentation

Version History

0.1.0

• Initial release
• Text-to-speech conversion
• Support for all MiniMax speech models
• Voice emotion control
• Multiple audio format support
• Voice cloning integration
• Comprehensive error handling