The application lets you use Microsoft's cognitive services, in this case vision and audio.
- For audio mode, there are three modes of operation, free mode, voice commands and math mode.
- With the vision mode it is possible to identify public figures.
To use the application, you need to install the following libraries:
- SpeechRecognition (pip install SpeechRecognition)
- PyAudio (pip install pyaudio)
- Requests (pip install requests)
- num2words (pip install num2words)
- Pillow (pip install pillow)
For use this application you need to have two Keys, Bing Vision API, and Bing Speech API. Go to Azure and grabe this two Keys to use this application.
Run the application with the follow command:
- python GUY.py