LingoSnap
A sophisticated, AI-powered personal learning assistant designed to accelerate studying. It transforms content from images or PDFs into interactive materials like flashcards and quizzes using Google's Gemini API. Suited for language learners and students, it features multi-modal analysis, intelligent PDF parsing, and interactive tools with text-to-speech.
Technologies
Architecture and delivery context
Problem
Students often work with fragmented materials — paper notes, flashcard apps, and lists that gradually lose their connection to the source. Building structured exam-ready material from a textbook page, a printed article, or a PDF still takes a lot of manual work.
Approach
LingoSnap turns photos and PDFs into ready-to-use study material. The user snaps a page, AI extracts the essence, and the result is saved into workbooks — containers that group flashcards, quizzes, and notes together and serve as a study unit for exams in any subject.
Each workbook has one of three modes, picked based on the learning goal:
- Language learning — vocabulary, grammar, and usage examples
- Q&A — study questions and answers generated from the material
- Knowledge base — key concepts and definitions from technical or academic texts
Stack
- Frontend: Angular + Tailwind, packaged as a PWA with Capacitor for iOS and Android
- Backend: NestJS + MongoDB
- AI: Google Gemini for content analysis and term generation, Google Cloud TTS for audio, OpenAI for image generation
- Billing: Stripe subscriptions and credits
Key Features
- Snap a photo or upload a PDF and get a workbook ready for studying
- Three workbook modes (language, Q&A, knowledge base) covering different types of study material
- Flashcards, quizzes, and notes organized inside each workbook
- Text-to-speech audio for pronunciation practice
- AI chatbot for grammar and context questions
- Teacher mode for managing student groups and sharing workbooks
- Free tier with local storage; paid tier unlocks cloud sync and AI credits
Outcome
A single mobile-first product that connects content capture, AI extraction, and active study into one workflow.