multilingual

AI-powered scam detection for Indian citizens — multilingual, free, and instant.

Utsav Kathalu is a web application built with Streamlit for collecting and organizing festival stories in multiple Indian languages. Users can submit stories as text, attach images for each section, and view the content as an interactive virtual book. The platform aims to preserve and present cultural narratives in a structured and user-friendly format.

AI Chat Assistant is a conversational platform built using Streamlit, designed to integrate multiple Large Language Models (LLMs) such as Ollama (local hosting), OpenAI, and Google Gemini. The system provides a flexible interface for seamless interaction across different models while supporting customization through fine-tuned domain-specific datasets. Its architecture emphasizes scalability, multilingual support (including Indic languages), and accessibility, making it suitable for both personal productivity and enterprise use.

This project is a real-time voice translator web application built with Streamlit. It captures live speech input via microphone, recognizes the spoken text using speech recognition, translates it to a selected target language via machine translation, and plays back the translated audio using text-to-speech synthesis. The app supports multiple languages, provides start/stop controls for continuous conversation flows, displays original and translated text, allows editing of transcriptions, and enables exporting of recordings and analysis. It aims to facilitate accessible, multilingual communication and contribute to language corpora for research purposes.

A creative Telugu dream journaling web app that allows users to write, rewrite, tag, and share dreams in poetic or story formats.

AI/ML-based tool that predicts the likelihood of diabetes using medical parameters such as glucose, BMI, age, and blood pressure.

The Image Captioning project is an AI-based system that automatically generates textual descriptions for images. It combines computer vision and natural language processing (NLP) techniques to understand the content of an image and produce a human-readable caption.

The system uses deep learning models, typically a Convolutional Neural Network (CNN) for extracting image features and a Recurrent Neural Network (RNN) or Transformer-based model for generating sentences. This enables applications such as assisting visually impaired users, enhancing image search engines, and automating social media content tagging.

A family recipe sharing app built with Python for managing and sharing recipes across family members.

SwechaBot: A conversational AI chatbot built with Streamlit, Hugging Face Transformers, and Torch

Basha Kahani

Basha Kahani is a storytelling web application that allows users to create, share, and explore short stories in an engaging and user-friendly way.

🔹 Features:

Add and publish your own stories.

View stories shared by other users.

Interactive UI with smooth navigation.

Built with modern web technologies for performance and scalability.

🔹 Tech Stack:

Frontend: React.js (with TailwindCSS for styling)

Backend (if applicable): Node.js / Express.js (or API integration)

Database (if applicable): MongoDB / Firebase / JSON-based storage

🔹 Project Goals: The main goal of this project is to provide a creative platform where users can express themselves through stories. It is designed to be simple, lightweight, and easy to use, while also serving as a learning project to practice React, component-based design, and UI/UX development.

Local Proverbs Collector is an open-source, AI-powered application that helps preserve and celebrate traditional Indian proverbs across multiple languages and dialects. The app allows users to contribute proverbs through text or voice, automatically transcribing speech, translating into other languages, and optionally reading them aloud using Text-to-Speech.Optimized for rural and low-connectivity areas, it supports offline-friendly usage, light/dark mode, and a gamified experience with leaderboards, streaks, and voting.All data is stored in structured JSON format for easy research, analysis, and integration into AI language models ensuring India’s oral heritage is preserved for future generations.

A simple chatbot built using Hugging Face and Streamlit that answers user queries about Indian temples. The app provides cultural, historical, and architectural insights in a conversational format.

A multilingual Streamlit-based AI assistant for farmers that provides weather forecasts, crop market prices, fertilizer recommendations, farming tips, and voice-enabled queries in Hindi, English, and Telugu.

BharatiBandhu (भारतीबंधु - "Friend of India") is an open-source AI assistant that democratizes access to practical knowledge for every Indian in their native language. This multilingual web application breaks down language barriers, making technology accessible to India's diverse population.

Project Description: A Streamlit-based Farmers Knowledge Corpus Engine to collect, preserve, and visualize traditional agricultural knowledge, remedies, folk practices, stories, and historical insights directly from farmers across India. The application allows farmers to submit knowledge in text, audio, video, or image formats, supports search and filtering by keywords, category, and language, and provides visual analytics such as word clouds, contribution maps, and category charts. Users can like entries, add comments, and export the corpus in CSV or JSON formats. The project aims to preserve indigenous knowledge for researchers, students, and agricultural communities while promoting community engagement and knowledge sharing.

Tags:Streamlit, Python, Agriculture, Knowledge Corpus, Data Visualization, Community Engagement, Open Source

This project, "Ruchi: Your Culinary Assistant," is a multilingual chatbot that provides cooking advice. Built with Streamlit in Python, it uses different Large Language Models (LLMs) for English and Telugu responses to offer culturally relevant recipes and tips.

A multilingual Streamlit app for collecting, displaying, and preserving regional proverbs across South Asia.

AI-powered offline-first Streamlit application for collecting corpus data (audio, video, image+caption, and text) in 11 Indian languages for SOAI 2025.

An open-source Streamlit chatbot app powered by Gemini API with multilingual support

"Tejaswi" is an open-source AI assistant that provides high-quality, accurate responses in nine major Indian languages. It solves the common problem of garbled text in Indic scripts by using a unique architecture: a powerful English-language model (Mistral-7B) for reasoning, combined with a real-time translation layer. This ensures users can interact fluently in their native language and receive reliable, coherent answers.