🎙️ SpeechConvert

Real-time Speech-to-Text with Translation and Emotion Detection

---

🧭 Table of Contents

• Overview
• Features
• Tech Stack
• Screenshots
• Getting Started
  • 1️⃣ Prerequisites
  • 2️⃣ Backend — Environment Setup
  • ⚙️ Backend — Install & Run (ASGI required)
  • 🚀 Running the Frontend

---

🧩 Overview

SpeechConvert is a full-stack web application that:

• Converts speech to text in real time using Whisper.
• Optionally translates the result into another language.
• Optionally detects emotion in the text.
• Allows users to record audio or upload files.
• Includes full user authentication (email + Google OAuth) and password reset.

---

🚀 Features

Feature	Description
🎤 Speech Recognition	Converts recorded or uploaded audio into text (via Faster-Whisper).
🌐 Translation	Uses Google Cloud Translate to convert text into multiple languages.
😊 Emotion Detection	Analyzes text with a HuggingFace emotion model.
🔐 Auth System	Register, login, logout, and password reset.
🔄 Token Refresh	Short-lived access tokens auto-refresh with cookies.
📁 Upload Audio	Supports MP3, WAV, and WEBM formats.
💾 Download Transcript	Exports transcript as a .txt file.

---

🧱 Tech Stack

Frontend

• React (TypeScript)
• Redux Toolkit
• React Router
• Axios (with token interceptor)
• Google OAuth

Backend

• Django 5 + Django REST Framework
• Django Channels (WebSockets)
• PostgreSQL
• Faster-Whisper
• HuggingFace Transformers
• Google Cloud Translate API
• FFmpeg for audio conversion

---

🖼️ Screenshots

Getting Started

Follow these steps to run SpeechConvert locally.

---

1️⃣ Prerequisites

• Python 3.10+
• Node.js 18+ and npm
• PostgreSQL 13+
• A Google Cloud Service Account JSON key with Translate API enabled
• ffmpeg binary available at backend/bin/ffmpeg (make it executable)

💡 On macOS/Linux you may need:
chmod +x backend/bin/ffmpeg

---

2️⃣ Backend — Environment Setup

Create a .env file inside the backend/ directory:

SECRET_KEY=your_secret_key
DEBUG=true
RENDER_EXTERNAL_HOSTNAME=localhost

DB_NAME=your_db
DB_USER=your_user
DB_PASSWORD=your_pass
DB_HOST=127.0.0.1
DB_PORT=5432

EMAIL_HOST=smtp.gmail.com
EMAIL_PORT=587
EMAIL_HOST_USER=your_email@gmail.com
EMAIL_HOST_PASSWORD=your_app_password
GOOGLE_APPLICATION_CREDENTIALS=/abs/path/to/service-account.json

⚙️ Backend — Install & Run (ASGI required)

cd backend
pip install -r requirements.txt
python manage.py migrate
python manage.py createsuperuser
daphne -b 0.0.0.0 -p 8000 backend.asgi:application

🚀 Running the Frontend

cd frontend
npm install
npm start