n8n Custom Nodes

A collection of custom n8n community nodes for AI-powered text, audio, and document processing.

📦 Included Nodes

Node	Description
Piper TTS	Convert text to speech using Piper TTS with multi-language support
Whisper	Transcribe audio files using OpenAI Whisper
Tesseract OCR	Extract text from PDF files with multi-language OCR support

---

🚀 Installation

Community Installation (Recommended)

1. Open your n8n instance
2. Go to Settings → Community Nodes
3. Click Install a community node
4. Enter n8n-custom-nodes and click Install

Manual Installation

npm install n8n-custom-nodes

Or install directly into your n8n custom nodes directory:

cd ~/.n8n/custom
npm install n8n-custom-nodes

---

📖 Node Documentation

🔊 Piper TTS

Converts text to speech using Piper TTS, a fast and local neural text-to-speech system.

Parameters

Parameter	Description
Input Text	The text content to convert to speech
Language	Select from Tamil, English, or use a custom model path
Custom Model Path	Path to your own .onnx model file (when "Custom" is selected)
Output File Path	Where to save the generated .wav audio file

Prerequisites

• Piper TTS installed and available in PATH
• ONNX model files for desired languages

Example Output

{
  "message": "Audio generated successfully",
  "outputFilePath": "/path/to/output.wav",
  "commandExecuted": "type \"input.txt\" | piper --model \"model.onnx\" --output_file \"output.wav\""
}

---

🎙️ Whisper

Transcribes audio files using OpenAI Whisper, supporting multiple models and output formats.

Parameters

Parameter	Description
Python Path	Path to Python executable (default: python)
Input File	Path to the audio file to transcribe
Output Directory	Directory to save transcription files
Model	Whisper model: tiny, base, small, medium, large, or turbo
Language	Language of the audio (e.g., "English", "Tamil")
Output Format	txt, vtt, srt, tsv, json, or all

Prerequisites

• Python 3.8+
• OpenAI Whisper installed: pip install openai-whisper

Example Output

{
  "stdout": "Detected language: English...",
  "stderr": "",
  "input_dir": "/path/to/audio.wav",
  "output_dir": "/path/to/output",
  "model": "base",
  "language": "English",
  "output_format": "txt"
}

---

📄 Tesseract OCR

Extracts text from PDF files using Tesseract.js, with support for multiple languages and page segmentation modes.

Parameters

Parameter	Description
Input Directory	Directory containing PDF files to process
PDF File Pattern	Glob pattern to match files (e.g., *.pdf)
From Page / To Page	Page range to process
DPI Resolution	Resolution for PDF to image conversion (72-600)
Language	OCR language: English, Tamil, Hindi, or combinations
Page Segmentation Mode	How Tesseract analyzes page layout
Output Options	Save TXT file, output directory, append mode, cleanup temp files

Prerequisites

• pdftoppm (from Poppler) installed and in PATH

Supported Languages

• English (eng)
• Tamil (tam)
• Tamil + English (tam+eng)
• Hindi (hin)
• Hindi + English (hin+eng)
• Custom language codes

Example Output

{
  "success": true,
  "directory": "/path/to/pdfs/",
  "language": "tam+eng",
  "psm": "SINGLE_COLUMN",
  "dpi": 300,
  "fromPage": 1,
  "toPage": 5,
  "filesProcessed": 2,
  "results": [
    {
      "pdfFile": "document.pdf",
      "text": "Extracted text content...",
      "outputFile": "/path/to/output/document.txt",
      "pages": [1, 2, 3, 4, 5]
    }
  ]
}

---

🛠️ Development

Prerequisites

• Node.js 18+
• pnpm (recommended) or npm

Setup

# Clone the repository
git clone https://github.com/JeyaramKumaravel/n8n-custom-nodes.git
cd n8n-custom-nodes

# Install dependencies
npm install

# Build the project
npm run build

# Watch mode for development
npm run build:watch

Available Scripts

Script	Description
npm run build	Build the nodes for production
npm run build:watch	Build in watch mode for development
npm run dev	Start development mode
npm run lint	Run ESLint
npm run lint:fix	Fix ESLint issues automatically
npm run release	Create a new release

Testing Locally with n8n

Follow these steps to test your custom nodes locally with n8n:

Step 1: Build and Link the Package

# Navigate to your custom nodes project
cd n8n-custom-nodes

# Install dependencies
npm install

# Build the project
npm run build

# Link the package globally
npm link

Step 2: Create the n8n Custom Nodes Directory

# Create the custom folder inside .n8n directory
# Windows (PowerShell)
mkdir ~/.n8n/custom

# macOS/Linux
mkdir -p ~/.n8n/custom

Step 3: Initialize and Link in the Custom Directory

# Navigate to the custom directory
cd ~/.n8n/custom

# Initialize a new package.json (required for npm link to work)
npm init -y

# Link the custom nodes package
npm link n8n-custom-nodes

Step 4: Restart n8n

# Restart n8n to load the new nodes
n8n start

Note: After making changes to your nodes, run npm run build in your project directory. The linked package will automatically reflect the changes after restarting n8n.

---

📁 Project Structure

n8n-custom-nodes/
├── nodes/
│   ├── PiperTTS/
│   │   ├── PiperTTS.node.ts
│   │   └── PiperTTS.svg
│   ├── Whisper/
│   │   ├── Whisper.node.ts
│   │   └── whisper.svg
│   └── TesseractOCR/
│       ├── TesseractOCR.node.ts
│       └── TesseractOCR.svg
├── icons/
├── package.json
├── tsconfig.json
└── README.md

---

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

---

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

---

👨‍💻 Author

Jeyaram Kumaravel

• GitHub: @JeyaramKumaravel
• Email: ramvel2002@gmail.com

---

🙏 Acknowledgements

• n8n - Workflow automation platform
• Piper TTS - Fast local neural TTS
• OpenAI Whisper - Speech recognition
• Tesseract.js - OCR engine