This package provide voice recognition and translation by using IBM Watson SpeechToText and LanguageTranslator Service.
It sends a PC speaker output to IBM Watson cognitive service, gets voice recognition results as text in real time and you have the option to choose whether to translate it or not.
It also exports the file to take the minites book as option.
Due to the self-restraint by COVID-19, I have developed it so that you can freely and comfortably watch video content and webinars in various languages around the world.
Therefore, it does not recognize the microphone input, only the speaker output.
This package has 3 activities:
- Speech To Text Streaming Scope
- Start Streaming Recognize
- Stop Streaming Recognize