Abstract: Audio to video conversion consists of the development of a contributory software for hearing aided people, Audio to video conversion records audio and produces sign language video of that audio. The goal of this application is to create the foundation for a spatial platform for aided people. The application has a user-friendly interface. A folder will consist of videos of alphabets and numeric sets, to convert each line into the sign language word by word. It is a standalone software for personal computers so no user database is maintained and no registration is required, but data of their previously converted audios is maintained. A line on the screen will appear prompting the user to give the input audio which has to be converted, the user can either say it or play the audio, you can also use earphones to give the audio input. This application records the audio maintaining a minimum threshold of audio using python packages like pyaudio and wave. The application will process the audio using the python library called speech recognition which will convert audio into text. Using the requests module of python we extract the video files from an online platform handspeak.com, moviepy.editor is being used for editing the video for giving the desired output. The python module shutil is used to copy the extracted video file into a folder called cache where the user can access the converted audio to video.
“Audio to video conversion” is developed using python and it’s advanced libraries. A simple atom editor is used for coding and importing the required modules.
Keywords: Interface, Standalone, Threshold, pyaudio, Shutil.
| DOI: 10.17148/IJARCCE.2020.9527