Speech to Spanish Translator

Web application for recording audio, transcribing speech (STT) and translating to Spanish.

Features

• 🎤 Audio recording from microphone
• 🗣️ Speech-to-text using OpenAI Whisper
• 🌍 Translation to Spanish using GPT
• ⚡ Real-time processing
• 🎨 Modern React interface

Tech Stack

• Frontend: React + TypeScript + Vite
• Backend: Node.js + Express + TypeScript
• AI: OpenAI API (Whisper + GPT)

Prerequisites

• Node.js 18+
• OpenAI API key

Installation

1. Clone repository

git clone <repository-url>
cd llm-stt

2. Backend Setup

cd backend
npm install
cp .env.example .env
# Edit .env and add your OPENAI_API_KEY

3. Frontend Setup

cd ../frontend
npm install

Running the Application

Start Backend (Terminal 1)

cd backend
npm run dev
# Server runs on http://localhost:5000

Start Frontend (Terminal 2)

cd frontend
npm run dev
# App opens on http://localhost:5173

Usage

1. Open http://localhost:5173 in browser
2. Click "Start Recording"
3. Speak in Russian
4. Click "Stop Recording"
5. Wait for transcription and translation
6. View results: original text and Spanish translation

API Endpoints

• POST /api/transcribe - Process audio file
  • Input: audio file (multipart/form-data)
  • Output: { originalText, translatedText }
• GET /health - Health check

Project Structure

llm-stt/
├── frontend/           # React application
│   ├── src/
│   │   ├── components/
│   │   │   ├── AudioRecorder.tsx
│   │   │   └── TranslationDisplay.tsx
│   │   └── App.tsx
├── backend/           # Node.js API
│   ├── src/
│   │   └── index.ts
│   └── .env.example
└── README.md

Environment Variables

Backend (.env):

• OPENAI_API_KEY - Your OpenAI API key
• PORT - Server port (default: 5000)

License

MIT