n8n-nodes-doubao

A community-developed n8n node package that integrates Doubao (ByteDance) Text-to-Speech services into your workflows.

Overview

This package provides n8n integration for Doubao TTS (Text-to-Speech) services, allowing you to convert text to high-quality audio directly within your n8n workflows.

Features

Doubao TTS Node

• 🎤 High-quality text-to-speech conversion
• 🗣️ Multiple voice options (male, female, emotional voices)
• 🎵 Multiple audio formats (MP3, WAV, PCM)
• ⚡ Adjustable speech rate, volume, and pitch
• 🌐 Multi-language support (Chinese, English, Japanese, Korean)
• 💫 Emotion control (happy, sad, normal)
• 📁 Custom filename support

Installation

# Install in your n8n project directory
npm install n8n-nodes-doubao

# Or install globally (if you have n8n installed globally)
npm install -g n8n-nodes-doubao

Prerequisites

• Node.js >= 18.19.0
• npm >= 9.x
• n8n >= 1.0.0

Quick Start

1. Restart your n8n service after installation
2. Find "Doubao TTS" node in the node panel
3. Configure API credentials (see configuration section below)
4. Start using!

API Configuration

Getting API Credentials

1. Visit Volcengine Console
2. Register and complete identity verification
3. Enable Speech Synthesis service
4. Obtain the following credentials:
   • Access Token: your_access_token_here
   • App ID: your_app_id_here
   • Cluster (optional): volcano_tts (default)

Setting up in n8n

1. In n8n interface, click "Credentials" → "+ New Credential"
2. Search and select "Doubao API"
3. Fill in your API credentials and save
4. Select this credential in the Doubao TTS node

Usage Examples

Basic Text-to-Speech

Input Text: "Welcome to Doubao Text-to-Speech service!"
Voice Type: BV700_streaming (Standard Female)
Output: MP3 audio file

Advanced Configuration

Input Text: "Congratulations on your achievement!"
Voice Type: BV700_streaming
Emotion: happy
Speed Ratio: 1.2 (slightly faster)
Volume Ratio: 1.5 (slightly louder)
Custom Filename: celebration_message

Node Parameters

Voice Options

| Voice Code | Description | Characteristics | |------------|-------------|-----------------| | BV700_streaming | Standard Female | Clear and natural, suitable for general use | | BV701_streaming | Standard Male | Stable and powerful, suitable for formal occasions | | BV001_streaming | Sweet Female | Gentle and lovely, suitable for friendly scenarios |

Audio Formats

| Format | Quality | Use Case | |--------|---------|----------| | mp3 | Good compression | Web applications, general use | | wav | High quality | Professional audio editing | | pcm | Raw audio | Audio processing, development |

Emotion Styles

| Emotion | Description | |---------|-------------| | normal | Standard neutral tone | | happy | Cheerful and upbeat | | sad | Melancholic tone |

Common Use Cases

| Scenario | Recommended Settings | |----------|---------------------| | News Broadcasting | Male voice + Normal speed + Normal emotion | | Audiobook Narration | Female voice + Slower speed + Gentle emotion | | Alert Notifications | Loud volume + Faster speed + Normal emotion | | Children's Content | Sweet female voice + Slower speed + Happy emotion |

Troubleshooting

| Issue | Solution | |-------|----------| | 🔑 Authentication failed | Check Access Token and App ID | | 🌐 Network timeout | Verify internet connection | | 📝 Text too long | Split text into smaller chunks | | 🎵 Audio quality issues | Try different voice types or formats |

Technical Details

• API Endpoint: https://openspeech.bytedance.com/api/v1/tts
• Authentication: Bearer token
• Response Format: JSON with base64 encoded audio data
• Binary Output: Compatible with n8n's binary data format

Integration with Other Nodes

The Doubao TTS node works seamlessly with:

• Telegram nodes (Send Audio/Voice messages)
• File nodes (Save audio files)
• HTTP Request nodes (Upload to external services)
• Email nodes (Send audio attachments)

Contributing

We welcome contributions from the community! Please feel free to:

• Report bugs and issues
• Suggest new features
• Submit pull requests
• Improve documentation

Roadmap

• [x] ✅ Basic Doubao TTS functionality
• [x] ✅ Multiple voice support
• [x] ✅ Emotion control
• [x] ✅ Custom filename support
• [ ] 🔄 Batch processing optimization
• [ ] 🔄 Audio caching mechanism

Support

• 📦 NPM Package
• 🐛 Issue Tracker
• 💬 Discussions

License

MIT License - see LICENSE file for details

Disclaimer

This is a community-developed package and is not officially affiliated with n8n or ByteDance/Volcengine. Use at your own discretion and ensure compliance with the respective service terms.