An Experimental Approach for Text to Speech Conversion


Dr. Mihir Narayan Mohanty
Siksha ‘O’ Anusandhan (Deemed to be University), Odisha, India.


This paper represents a document/print reader for visually weakened individual, established on “Raspberry Pi”. The “Optical character recognition” technology is used in the particular system for recognition of print/written characters by employing images capturing apparatus & computer programming. This project transforms image of the printed, captured or the handwritten characters to machine coded characters. These documents are transformed to acoustic outcome (speech) by employing OCR & “Text-to-speech synthesis”. This transformation of the paper into text forms are performed by employing “Raspberry Pi” that further utilizes the “Tesseract library” & “Python programming”. The Opencv processes the character files using its library and “Python programming language” and further acoustic outcome is attained.