Getting Started with Google Cloud Speech-To-Text API in Python

In this tutorial, I will be covering how to get started with Google Cloud Speech-To-Text API in Python.

Speech-To-Text is one of the Google Cloud Service products. Using the Speech-To-Text API, we will be able to transcribe media files (audio to text converter) such as MP3, MP4, Wav files or transcribing when we are streaming a podcast (voice to text feature). And since I am trying to keep to the tutorial short, I will only cover the things I think are the most important.

PS: Forgot to mention one really important factor in the video that affects the pricing. Each audio channel is billed separately. If you send requests with multiple channels, you will be billed according to the sum total length of audio processed from all channels. For example, a wav file is a 2 channel audio sound file, therefore, each channel is charged separately.

Timestamps:
00:00 - Google Cloud Speech-To-Text Introduction
00:50 - Speech-To-Text Pricing
02:49 - Speech-To-Text Quotas and Limits
03:30 - Enable Cloud Services in Google Cloud Console
05:28 - Install Google Cloud Speech-To-Text Python Library
06:03 - Speech-To-Text API example 1 & 2 (transcribing local media files)
20:13 - Speech-To-Text API example 3 (transcribing long media files)

Useful Links:
-------------------------

Buy Me a Coffee? Your support is much appreciated!
-------------------------------------------------------------------------------------
🔑Venmo: @Jie-Jenn

Support my channel so I can continue making free contents
---------------------------------------------------------------------------------------------------------------

#GoogleCloud #TextToSpeech #Text-To-Speech #GoogleAI #Python

[moreirarossi]

Meu amigo, quero agradecer imensamente por este video. Assinei o período gratis do Google Cloud para ver se tinha mais detalhes de como usar a api, e
Nem o próprio google explica tão bem!!
Parabéns e muito obrigado.

[Zephyrpardiez]

Hello. Help me. I configured the authentication and the path or address of the key but after deleting the key by mistake, no matter how much I try to change the address of the key, it keeps indicating that I need to change the address or path of the key, but I already changed it. I already made a request with a new password and everything, but no matter how many times I change the address to the new password, it still indicates as if the address were that of the deleted password. I don't know how to restore or reset that, it's like it's impossible to change the path of the key I deleted.

[vibhorejain]

Thanks for putting this out and sharing the source code! Was very helpful.

[mysterious_monolith_]

Good tutorial. Many others only cover -text-to-speech API not speech-to-text API.

[yaboobayyaboobay]

Why the sample hertz for the long wave is set to 48000 and not 44100?

[PratikBhalerao-rzpm]

Excellent. How can we get the raw lexical output from API without number formatting ?

[robc]

A sample that works with microphone would be good

[yaelefrat]

thank you so much for that video! it is beneficial. I have a question: I saw your videos on Google Drive API and was wondering if it is possible to transcribe a long video that is stored on Google Drive? (on a shared folder so it is not on myDrive so I can't access it on my PC)

[juanandreslopezcubides]

Hi, I have this error ValueError: Unknown field for RecognitionConfig: enable_Automatic_Punctuation

[sumukhvshankar]

where did you download client service key. json file from?

[novicevoyager]

sir could you please make a tutorial on how to convert Real time Voice-to-text in Python using google cloud speech to text.. I have searched everywhere but couldn't find one

[kavyamehta]

I am getting this error when I ran the pip install --upgrade google-cloud-speech command: ERROR: Cannot uninstall 'PyYAML'. It is a distutils installed project and thus we cannot accurately determine which files belong to it which would lead to only a partial uninstall.

Any idea how I can fix it?

[ERRORHA]

thank you for your work it is really helpful I am a senior and I need to work on this for my project and this is a really good tutorial, but if you don't mid telling me about where to get or how to make the .bat file I would be thankful!

[LulululuZzzz]

Why the file size has to be less than 1 min? What about longer videos?

[naziyashaik]

Great, How to give the input from microphone can you help me with this

[martinlastname]

Where did you Client service key come from?

[balajicmb]

Sir could you please make a tutorial on how to audio file to text conversion using open source library python?

[AlhamedCraft]

bro i thank you for your work. and im sure u will do better work in future. ill be very thankful if you can make your tutorials little bit more simple, as me a new programmer alot of what your doing i dont know what is it and u r bringing things from where u installed it like the json thingy? thank you

[ananthnm]

can you pls help because i get error when installing google-cloud-speech