Real-time Transcription Playground

A real-time transcription project using React and a socketio python server. The goal of this project is to enable developers to create web demos and speech2text prototypes with just a few lines of code. Examples can be medical dictation apps, a note-taking CRM for entrepreneurs, etc.

Currently only supports real-time transcription using Google Cloud Speech



Google Speech API

The code assumes an environment variable GOOGLE_SERVICE_JSON_FILE that points to a valid GCP service account file.

If you need to get a service account:

  • Within your Google Cloud console, create or select a project
  • Enable the Cloud Speech API for that project
  • Create a service account
  • Download a private key as JSON

More info in Google Cloud's docs here and here.

Then, set the environment variable GOOGLE_SERVICE_JSON_FILE to the path of the JSON file containing your service account key, e.g. /users/sahar/documents/sample-project-3c1a5892b00e.json. Further details can be found in this Medium article.


  1. Clone or fork this repository
  2. Create a virtual environment in the root directory: python -m venv $ENV_NAME
  3. Activate the virtual environment: source $ENV_NAME/bin/activate (for MacOS, Unix, or Linux users) or .\ENV_NAME\Scripts\activate (for Windows users)
  4. Install requirements: pip install -r backend/requirements.txt
  5. Set your environment variable GOOGLE_SERVICE_JSON_FILE to point to your file path
  6. Run yarn install in the root directory
  7. Run yarn start to start the frontend and start-backend to run the backend