Skip to content

Yatendra-Gupta193/Automated_Content_Localization

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

17 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

🌍 Automated Content Localization Platform

An AI-powered localization platform that adapts Text, Voice, and Visual Content for different languages, cultures, and regions using Generative AI, OCR, and Speech Processing.

This project was developed as a Mini Project (AIML) 2025-2026 using Flask, Gemini API, EasyOCR, Speech Recognition, and AI-based localization techniques.


πŸ“Œ Project Overview

The Automated Content Localization Platform helps users localize different types of content:

  • πŸ“ Text Localization
  • 🎀 Voice Localization
  • πŸ–ΌοΈ Visual Localization

The system provides:

  • AI-generated multilingual localization
  • Region-specific cultural adaptation
  • OCR-based text extraction from images
  • Speech-to-Text and Text-to-Speech conversion
  • Tone-aware content generation

πŸš€ Features

βœ… Text Localization

  • Translate and localize text
  • Supports multiple tones
  • Region-aware adaptation
  • AI-generated culturally relevant output

βœ… Voice Localization

  • Upload audio files
  • Speech-to-Text conversion
  • AI localization processing
  • Text-to-Speech generated localized audio

βœ… Visual Localization

  • Upload image files
  • OCR text extraction using EasyOCR
  • Detect image context
  • Generate localized captions and UI text
  • Cultural notes generation

πŸ› οΈ Tech Stack

Backend

  • Python
  • Flask

Frontend

  • HTML
  • CSS
  • JavaScript
  • Jinja2 Templates

AI Integration

  • Google Gemini API

OCR & Image Processing

  • EasyOCR
  • Pillow (PIL)
  • OpenCV

Voice Processing

  • SpeechRecognition
  • gTTS
  • pydub

πŸ“‚ Project Structure

Automated-Content-Localization/
β”‚
β”œβ”€β”€ app.py
β”œβ”€β”€ requirements.txt
β”œβ”€β”€ README.md
β”œβ”€β”€ .env
β”œβ”€β”€ .gitignore
β”œβ”€β”€ image.jpeg
β”œβ”€β”€ activate.bat
β”œβ”€β”€ library_list.txt
β”‚
β”œβ”€β”€ services/
β”‚   β”œβ”€β”€ gemini_service.py
β”‚   β”œβ”€β”€ voice_service.py
β”‚   β”œβ”€β”€ visual_service.py
β”‚   └── ocr_service.py
β”‚
β”œβ”€β”€ templates/
β”‚   β”œβ”€β”€ home.html
β”‚   β”œβ”€β”€ text.html
β”‚   β”œβ”€β”€ visual.html
β”‚   β”œβ”€β”€ voice.html
β”‚   β”œβ”€β”€ result.html
β”‚   └── feedback.html
β”‚
β”œβ”€β”€ static/
β”‚   β”œβ”€β”€ css/
β”‚   β”œβ”€β”€ uploads/
β”‚   └── outputs/
β”‚
β”œβ”€β”€ instance/
β”‚
└── Visual-Backend/

βš™οΈ Installation Setup

1️⃣ Clone Repository

git clone <repository-link>
cd MINI_PROJECT_2Y-MAIN

2️⃣ Create Virtual Environment

Windows

python -m venv venv
venv\Scripts\activate

Linux / Mac

python3 -m venv venv
source venv/bin/activate

3️⃣ Install Dependencies

pip install -r requirements.txt

πŸ”‘ API Configuration

This project uses the Google Gemini API for AI-based localization.

Create .env File

Create a .env file in the project root directory.

Example:

GOOGLE_API_KEY=your_gemini_api_key_here

Get Gemini API Key

  1. Visit: https://aistudio.google.com/app/apikey

  2. Generate your API Key

  3. Copy and paste it inside the .env file


▢️ Run the Project

Start the Flask application:

python app.py

Open browser:

http://127.0.0.1:5000/

🌐 Supported Modules

πŸ“ Text Localization

Input

  • Original Text
  • Target Language
  • Region / Culture
  • Tone

Output

  • Localized Text
  • Cultural Adaptation

🎀 Voice Localization

Input

  • Audio File / Voice Recording
  • Target Language
  • Region
  • Tone

Output

  • Transcribed Text
  • Localized Voice Output
  • Generated Audio File

πŸ–ΌοΈ Visual Localization

Input

  • Image Upload
  • Optional Caption / UI Text
  • Target Language
  • Tone

Output

  • Extracted OCR Text
  • Localized Visual Caption
  • Cultural Notes

🎭 Supported Tones

Text Module

  • Formal
  • Casual
  • Marketing
  • Narrative
  • Professional

Visual Module

  • Formal
  • Casual
  • Professional
  • Friendly

🧠 Working Flow

Text Localization Flow

User Input
   ↓
Gemini AI Processing
   ↓
Localization Generation
   ↓
Cultural Adaptation
   ↓
Final Output

Voice Localization Flow

Audio Upload
   ↓
Speech-to-Text
   ↓
AI Localization
   ↓
Text-to-Speech
   ↓
Localized Voice Output

Visual Localization Flow

Image Upload
   ↓
OCR Text Extraction
   ↓
Image Context Understanding
   ↓
AI Localization
   ↓
Localized Visual Output

πŸ“Έ Preview

Home Page Preview

Project Preview


πŸ” Example Use Cases

  • Educational content localization
  • Voice translation systems
  • Multilingual customer support
  • Marketing localization
  • Visual content adaptation
  • Regional UI localization

---"# Automated_Content_Localization"

About

Developed an AI-powered Automated Content Localization Platform that supports Text Localization, Voice Localization, and Visual Localization. The system leverages OCR, Speech Recognition, Text-to-Speech, and Google Gemini AI to provide context-aware, multilingual, and culturally adapted content for global audiences....

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Contributors