Transcribe Audio and Use Speech Recognition in Python

Have you ever wondered how to add speech recognition to your Python project? Transcribing an audio file, or your microphone's input. It’s more straightforward than you might think. In this video you'll learn how to install and use the SpeechRecognition package—a full-featured and straightforward Python speech recognition library.

[idk____idk]

To the world, you may be just a teacher but to me, you are a hero! Wishing you a Happy Guru Purnima! I bow to the one who has inspired me and taught the right way of life! You are the inspiration who made me overcome every hurdle in python ❤️

[yonnialvarez]

how can i get the whole pc audio transcribed instead of just the microphone?

[sinopulence]

Awesome! How would you go about transcribing audio, but registering a dictionary of timecodes to audio file, so you can isolate a single word or phrase, then returning the audio clip?

[jarodmorris]

And what do you do when your audio file is 20+ seconds long and recognize_google() is only giving you the first 2-3 seconds transcribed?

[leenjogu]

@Real Python how do i add an audio file to the code for transcription

[somename]

Thanks for the tutorial. I got the following text which is not correct. Could please let me know why I am getting incorrect recognition?
'the still smell of old beer drinkers it takes hi to bring out the order I called it yourself invest a salt a kotess find the M tacos Al pastor my favourite is just for food is Bihar cross bun'

[thiagosannafreiresilva]

Now let's see if it can recognise Scottish English 😁.