This software detects user faces, emotions and speech in real-time (near real-time) using APIs from Microsoft Cognitive Services. The application is implemented in Python (from version 3.5), and use OpenCV package for webcam support and PyAudio for microphone support.
- Get API keys for the Emotion APIs and the Face APIs from microsoft.com/cognitive:
- Open the setenv_example.sh file and add the three API Keys as environment variables. Execute the script.
- Run the client.py script