Speech analysis tool coded in Python - modified version of Shahabks/my-voice-analysis.
pySpeechAlien can analyze .wav audio files to determine gender, mood, speech rate, pronunciation probability score, etc.
To get this tool up and running on your local machine, follow the below instructions. pySpeechAlien should work with both Python 2.7+ and Python 3, but if you have issues, please create an issue, and I'll promptly help you out.
Install pySpeechAlien using pip.
>>> pip install pySpeechAlien
Upgrade to the latest version using pip.
>>> pip install -U pySpeechAlien
Download myspsolution.praat and run_speech_alien.py, and move them to the folder containing your .wav audio files.
Look below to see how to run run_speech_alien.py.
>>> python run_speech_alien.py -h Type python run_speech_alien.py, followed by one of these tags and the name of a .wav audio file, to get your desired output. [EXAMPLE INPUT] python run_speech_alien.py -speech_rate alien.wav You can also analyze multiple audio files. [EXAMPLE INPUT] python run_speech_alien.py -speech_rate alien.wav human.wav -h Get list of commands for pySpeechAlien -full Run full analysis -gender Determine gender -mood Determine mood -syllables Determine number of syllables -pauses Determine number of pauses -total_duration Determine total duration (seconds) -speaking_duration Determine duration of actual speaking (seconds) -silent_duration Determine duration of silence (seconds) -speech_rate Determine speech rate (number of syllables / seconds of speaking duration) -pause_rate Determine pause rate (number of pauses / seconds of silent duration) -speaking_to_total Determine ratio of speaking duration to total duration -pronunciation Determine pronunciation probability score