PicToSpeech is an Android app designed to help visually impaired users understand English and Turkish texts in images. The app uses Google’s ML Kit for character recognition, TTS (Text-to-Speech) libraries for audio output, and extracts context from text using the Gemini LLM API. Users can take photos of text, and the app reads it aloud in a natural voice.
- 📷 Image Text Recognition – Extracts text from images using Google ML Kit
- 🔊 Text-to-Speech – Reads the extracted text aloud in English and Turkish
- 🤖 Contextual Understanding – Uses Gemini LLM API for better comprehension
- 🌐 Bilingual Support – English and Turkish texts supported
- 📥 Offline APK Installation – Users can download and install the APK
- OCR, TTS, Prompt Engineering
The app APK can be downloaded directly from the repository:
Instructions:
- Download both
.z01and.zipfiles. - Extract the files using an archive tool (WinRAR, 7-Zip, etc.).
- Install the APK on your Android device (enable “Install from unknown sources” if required).
- Clone the repository:
git clone https://github.com/yourusername/PicToSpeech.git
- Open the project in Android Studio.
- Sync Gradle and build the project.
- Run on a physical device or emulator.
✅ Completed (2024) – Available for download and installation.
Made with ❤️ using Android Studio, ML Kit, and Gemini API
Do you want me to do that?