A personal learning project built using Apple Vision Framework, Natural Language Kit, and AVSpeechSynthesizer to scan printed text, detect its language, and read it aloud using text-to-speech.
This app is part of my journey to explore machine learning and natural language processing on-device with Apple technologies.
-
📷 OCR with VisionKit
Capture and extract text from camera input or images using Apple’s built-in Vision framework. -
🌐 Language Detection
Automatically detects the primary language of the scanned text usingNLLanguageRecognizer. -
🔊 Text-to-Speech (TTS)
Reads the scanned text aloud in the detected language usingAVSpeechSynthesizer. -
🧠 On-device Processing
All text recognition and language detection happen on the device, ensuring fast performance and user privacy.
| Technology | Description |
|---|---|
| Swift & SwiftUI | Declarative UI and application structure |
| Vision Framework | OCR (Optical Character Recognition) |
| Natural Language Kit | Language Identification |
| AVFoundation | Text-to-Speech via AVSpeechSynthesizer |
Coming soon...
- OCR via Camera
- Language Detection
- Text-to-Speech Output
- Multi-language support fallback
- UI refinement and animations
- Export scanned text as file
I'm currently learning how to build intelligent iOS apps using Apple frameworks that support computer vision and natural language processing. This project is a playground for me to explore:
- OCR and live camera integration
- Local-only NLP (Natural Language Processing)
- Voice feedback systems for accessibility
This project is for learning purposes and is open to collaboration.
Feel free to fork, contribute, or reach out for questions!