Skip to content

Technical Documentation

Toby Benjamin Clark edited this page Jul 19, 2023 · 9 revisions

Accessibility Interface & Features

Facial Recognition

MeMa3 Facial Recognition uses the cv2 and face_recognition library. The code is based on this example, and has been consolidated into the facial_recognition class in codebank/mema_facial_recognition.py.

Speech Recognition

MeMa3 Speech Recognition uses the SpeechRecognition library, to use this call the listen(callback: function command in mema_speech_recognition.py and provide a function to callback to. Currently issues regarding muting ALSA output in terminal.

Text-To-Speech

MeMa3 Text to Speech uses the gTTS (Google Text To Speech) Library. This processes and generates audio offline and is available through the functions in mema_text_to_speech.py. For most purposes, calling the speak(text: str) function, which plays the given string asynchronously on a separate thread.

Clone this wiki locally