This project consists of a frontend and backend application designed to transcribe audio from uploaded files, recorded audio, or live audio streams using Deepgram's speech-to-text API.
root/
├── dg-frontend/ # React application for handling transcription
├── dg-backend/ # Node.js Express backend connecting to Deepgram SDK
└── postman collection/ # Postman requests collection for API testing
The frontend is a React-based web application that allows users to:
- Upload audio files for transcription.
- Record audio and send it for transcription.
- Stream live audio for real-time transcription.
The backend is a Node.js Express application that connects to the Deepgram SDK to process audio and return transcription results to the frontend.
A Postman collection is available to test the Deepgram’s API endpoints.