VOCAL INPUT TO TEXT OUTPUT: A USER-FRIENDLY DESKTOP APPLICATION

Abstract

The creation of a desktop voice-to-text program that facilitates the conversion of spoken speech into written text is the main goal of this final project. The system's dual support for English and Indonesian fills a frequent flaw in many current solutions that ignore multilingual functionality. The application provides a straightforward and easy-to-use solution for anyone who require hands-free typing for accessibility, multitasking, or convenience, particularly for people with disabilities.. The project employs a Python-based desktop interface created with Tkinter in conjunction with Google's Speech Recognition API to do this. The way the system operates is by using a microphone to record audio, processing it in real time, and then turning the voice into text. The application allows users to read the transcription, save the text to a file, and choose their favorite language. According to the results, the program is a workable solution for hands-free text input because it can effectively transcribe speech for both supported languages. The gadget offers users a dependable and convenient method of typing without using their hands, even though ambient noise may compromise its accuracy and it necessitates an internet connection. For now, the system fulfills its promise to increase user convenience and accessibility, while future enhancements might include noise reduction, offline support, and multilingual support.