n8n-nodes-volcano-tts

This is an n8n community node that lets you use Volcano Engine TTS (Text-to-Speech) service in your n8n workflows.

Volcano Engine TTS is a powerful text-to-speech service that provides natural-sounding voices in Chinese and English, powered by ByteDance's AI technology.

n8n is a fair-code licensed workflow automation platform.

Installation

Community Node (Recommended)

1. Go to Settings > Community Nodes
2. Select Install
3. Enter n8n-nodes-volcano-tts in the input field
4. Select Install

Manual Installation

To install the node manually in a local n8n instance:

npm install n8n-nodes-volcano-tts

Prerequisites

You need to have a Volcano Engine account and obtain the following credentials:

• APP ID: Your application ID from Volcano Engine console
• Access Token: Your access token for authentication
• Cluster ID: The cluster ID for your TTS service (default: volcano_tts)

Operations

Text to Speech

Convert text to natural-sounding speech with various voice options.

Parameters:

• Text: The text to convert to speech (max 2000 characters)
• Voice: Choose from various Chinese and English voices
• Format: Audio output format (MP3, WAV, PCM, OGG)
• Sample Rate: Audio sample rate (8000-48000 Hz)
• Speed: Speech speed (0.5-2.0)
• Volume: Volume level (0-100)
• Pitch: Pitch adjustment (-12 to +12)

Supported Voices

Chinese Voices

• BV700_V2_streaming: 通用女声 (General Female)
• BV701_V2_streaming: 通用男声 (General Male)
• BV123_V2_streaming: 甜美女声 (Sweet Female)
• BV120_V2_streaming: 动感男声 (Dynamic Male)
• BV119_V2_streaming: 自然女声 (Natural Female)
• BV115_V2_streaming: 沉稳男声 (Steady Male)

English Voices

• BV001_V2_streaming: English Female
• BV002_V2_streaming: English Male

Usage Example

Basic Text-to-Speech Workflow

1. Add a Volcano TTS node to your workflow
2. Configure your credentials:
   • APP ID: Your Volcano Engine APP ID
   • Access Token: Your access token
   • Cluster ID: volcano_tts (or your custom cluster)
3. Set the text you want to convert
4. Choose a voice
5. Execute the workflow

Example with Dynamic Text

{
  "nodes": [
    {
      "parameters": {
        "text": "={{ $json.message }}",
        "voice": "BV700_V2_streaming",
        "additionalOptions": {
          "format": "mp3",
          "speed": 1.0,
          "volume": 50
        }
      },
      "name": "Volcano TTS",
      "type": "n8n-nodes-volcano-tts.volcanoTts",
      "position": [450, 300]
    }
  ]
}

Connection Modes

The node supports two connection modes:

1. WebSocket (Streaming): Real-time streaming synthesis with lower latency
2. HTTP (Standard): Traditional request-response pattern with higher stability

Output Options

The node can output audio in two ways:

1. Binary Data: Audio file as binary data (default)

   • Can be saved to disk or passed to other nodes
   • Preserves original audio quality

2. Base64 String: Audio encoded as base64 string

   • Useful for embedding in JSON responses
   • Can be decoded by other applications

Error Handling

The node includes comprehensive error handling for:

• Authentication failures
• Text length exceeding limits
• Network timeouts
• Invalid parameters
• API rate limits

Development

To build the node for development:

# Install dependencies
npm install

# Build the node
npm run build

# For development with watch mode
npm run dev

Testing

# Run linter
npm run lint

# Format code
npm run format

Publishing

To publish a new version to npm:

# Update version
npm version patch/minor/major

# Build and publish
npm publish

Resources

• n8n community nodes documentation
• Volcano Engine TTS Documentation
• GitHub Repository

License

MIT

Support

If you have any issues or questions, please:

1. Check the documentation
2. Open an issue on GitHub
3. Join the n8n community forum