An application which comes with features such as real-time speech recognition, real-time translation, text editing and saving audio files.

Program Type: Desktop Application

program specification: pyqt5

Back-end language used: Python 2.7 and above

Internet connection required: required because it uses the client-server API

Supported OS: Linux, Windows, Mac OS

Key APIs and Libraries used:

Google cloud speech API - uses a powerful neural network model with an easy-to-use API, enables developers to convert audio into text. This API supports the global user base by recognizing more than 120 languages and dialects.It can be used to implement voice commands and controls, to convert audio from call center to text, and use Google's Machine Learning technology to handle real-time streaming or pre-recorded audio.

Google cloud translation API - can dynamically translate text between thousands of language combinations. It allows users to integrate websites and programs with translation services in a programmatic manner. *Json file and Google Cloud SDK folder - the former is required for credentials and the latter is required for importing the appropriate python modules in the source code

Virtual Environment: Virtual environment was used to install all the required modules and eventually run the program. The commands made on linux terminal include:

“virtualenv takeClass”

“source takeClass/bin/activate”