priyanshu9898 / audio-accuracy-detection

Audio Transcription API using Google Cloud Speech-to-Text

Live Website: https://audioaccuracy.vercel.app/

Example Audio files: https://drive.google.com/drive/folders/1DY1KaX4XciukKL1rQicnHzS1b_vxjxpw?usp=sharing

Project Description:

This project is a simple RESTful API that allows users to upload audio files and transcribe them using Google Cloud Speech-to-Text service. The API receives an audio file and returns a transcription of the content. The project is built with Node.js, Express, and Google Cloud Speech-to-Text API.

Table of Contents

1. Requirements
2. Installation
3. Usage
4. API Endpoints
5. Contributing
6. License

Requirements

Node.js v14.x or later
Google Cloud Platform account with Speech-to-Text API enabled
Google Cloud SDK (gcloud) installed and configured

Run Locally

Clone the project

  git clone https://github.com/Priyanshu9898/PlayPower-Labs-Assignment

Go to the project directory

  cd PlayPower-Labs-Assignment

Go to the frontend directory and Install dependencies

  cd frontend

  npm install

Go to the backend directory and Install dependencies

  cd backend

  npm install

Set up Google Cloud authentication:

Download the JSON key file from Google Cloud Console for your service account.

Set the environment variable GOOGLE_APPLICATION_CREDENTIALS to the path of the JSON key file. For example, on Linux or macOS:

export GOOGLE_APPLICATION_CREDENTIALS="/path/to/your/keyfile.json"

Or on Windows (PowerShell):

$env:GOOGLE_APPLICATION_CREDENTIALS="C:\path\to\your\keyfile.json"

Usage

Start the frontend server

  npm start

Start the backend server

  npm run dev

Environment Variables

PORT: PORT number

Tech Stack

Client: React, react-bootstrap, tsparticles

Server: Node, Express

Database: MongoDB

API Reference

Get all items

  POST /api/v1/transcribe

Upload an audio file and receive a transcription of the content.

Request: Content-Type: multipart/form-data

Parameter	Type	Description
file	binary	Required. The audio file

Response: Content-Type: application/json

Parameter	Type	Description
transcription	string	Required. The transcribed text of the audio

Screenshots

Badges

Add badges from somewhere like: shields.io

🔗 Links

Demo

Insert gif or link to demo

License

MIT