RealTimeSpeechToText

This repository contains a Real-Time Speech-to-Text application built with Next.js for the frontend and Python Flask for the backend. The system captures audio input from the user and transcribes it into text in real-time using speech recognition technologies.

Note:

The installation steps are only allowed in ubuntu machine.

Installation (Run Backend):

Clone the application.

git clone https://github.com/harshadladva97/RealTimeSpeechToText.git
cd RealTimeSpeechToText

Install flask in the python.

For ubuntu:

pip install virtualenv
virtualenv venv
source ./venv/bin/activate
pip install flask flask-cors eventlet SpeechRecognition pyaudio # Install all the required packages.

Run the backend using following command:

python3 app.py

Installation (Run Frontend):

Go to the frontend folder in the application.

cd frontend`

Install npm packages.

pnpm install

Run the frontend application.

pnpm run dev

Open the browser with http://127.0.0.1:3000.

Use cases:

The application use the microphone to record the speech and transcribing the recording into the text.
It will transcribing text in realtime. (Note: If you don't catch the text then please check your microphone, background noise and your words should be very clear for understanding)

How to use: