VoiceToNote – LemonFox Whisper Transcription Tool

This repository provides two options for transcribing audio using the LemonFox Whisper OpenAI API:

1. Legacy Desktop App (legacy/ folder)
   For small files — a GUI app built with PyQt5 and direct API calls.

2. Callback-based Flask Server (in server/, suitable for deployment on cPanel or any WSGI server)
   For large files — uses a callback endpoint so LemonFox can notify when transcription is ready. A web dashboard displays results and lets you download .txt files.

---

🚀 Live Demo

---

Local Setup (Python 3.10+)

# 1. Create and activate a virtual environment
python -m venv myenv
source myenv/Scripts/activate  # On Windows use: .\myenv\Scripts\activate

# 2. Install dependencies
pip install -r requirements.txt

# Or install manually

# Server dependencies
pip install flask jinja2 python-dotenv

# Application dependencies
pip install PyQt5 ffmpeg-python requests-toolbelt

Project Structure

.
├── server/
│   ├── callback_server.py       # Flask server logic (WSGI-compatible)
│   ├── templates/
│   │   └── dashboard.html       # Jinja2 template for web UI
│   └── __init__.py              # optional, for modularization
├── app.wsgi                     # WSGI entry point for cPanel
├── legacy/
│   └── ...                      # PyQt5 desktop app
├── requirements.txt
└── README.md

How the Callback Server Works

1. Upload your audio using the desktop app or directly via API.
2. LemonFox processes it asynchronously and sends a callback to:
   https://yourdomain.com/callback
3. Your Flask server receives the callback and stores the transcription in memory.
4. You can view and download the result from the web dashboard as a .txt file.

Environment Variables

Create a .env file (excluded from repo) and include:

LEMONFOX_API_KEY=your-key-here
CALLBACK_URL=https://your-deployed-server-url/callback

🌐 Running the Server

🔹 Option 1: cPanel Deployment (WSGI)

To deploy the Flask callback server on cPanel:

1. Modify callback_server.py

Make sure it ends with:

application = app  # Required for WSGI

Remove or comment out app.run(...) if present.

2. Create app.wsgi in the root or server folder

import sys
sys.path.insert(0, "/home/your_cpanel_user/VoiceToNote/server")  # Adjust this path

from callback_server import application

1. Go to "Setup Python App"
2. Choose a Python version (e.g., 3.11+)
3. Set the Application Root to VoiceToNote/server
4. Set Application Startup File to callback_server.py
5. Set the Entry Point to application
6. Click Create Application
7. Open the terminal from cPanel and run: pip install -r requirements.txt

Option 2: Render Deployment (ASGI)

• The current server uses Flask (WSGI). If you'd like to deploy with FastAPI (ASGI) instead, feel free to reach out for help with refactoring.
• Give Render access to the current github repository.
• Match up the build deployment of render with this:

services:
  - type: web
    name: voice-to-note-fastapi
    env: python
    buildCommand: pip install -r requirements.txt
    startCommand: uvicorn callback_server:app --host 0.0.0.0 --port 10000
    plan: free
    envVars:
      - key: LEMONFOX_API_KEY
        value: your-api-key-here
      - key: CALLBACK_URL
        value: https://your-render-url/callback

Notes

• The desktop app is for smaller audio files and quick tests
• The server is ideal for longer recordings via asynchronous callback
• All transcriptions are downloadable as .txt files via the dashboard

📄 License

This project is licensed under the MIT License. See LICENSE for details.