ScribeAR Node Server

Backend for ScribeAR. Handles transcribing audio stream and rebroadcasting transcriptions to multiple devices.

Getting Started

• See README.md in /node-server and /whisper-service folders for detailed instructions for installation, development, and usage.

Usage

All-in-one Deployment

Deploys node-server, whisper-service, and ScribeAR frontend to be running on the same system.

Setup

1. Install Node 20, Python 3, and Google Chrome using official methods
   • https://nodejs.org/en/download
   • https://www.python.org/downloads/
   • https://www.google.com/intl/en_au/chrome/
2. Clone this repository

   git clone https://github.com/scribear/ScribeAR-NodeServer
   

3. Setup whisper-service

   cd ScribeAR-NodeServer/whisper-service
   

   python3 -m venv .venv
   

   . .venv/bin/activate
   

   pip install -r requirements.txt
   

4. Install requirements for the whisper implementations you want to use. See Installing Whisper Service Dependencies for details.

   pip install -r models/{model_implementation}_requirements.txt
   

5. Make a copy of template.env and name it .env
   • Edit .env according to Whisper Service Configuration
6. Build node-server

   cd ../node-server
   

   npm install
   

   npm run build
   

7. Make a copy of template.env and name it .env
   • Edit .env according to Node Server Configuration
   • Ensure port, api_key, and model_key match between whisper service and node server configurations.
8. The aio-autostart.sh script can then be used to start whisper service, node server, and google chrome automatically. Set this to automatically run on login with a user that is automatically logged in to have a hands free startup.
   • For Ubuntu, this can be achieved using by creating the following file at ~/.config/autostart/aio-autostart.desktop

     [Desktop Entry]
     Type=Application
     Exec= { PATH TO aio-autostart.sh SCRIPT }
     NoDisplay=false
     X-GNOME-Autostart-enabled=true
     Terminal=true