Google Cloud Speech-To-Text API With Python For Beginners

With Google Speech-To-Text API, you can convert speech to text, transcribe videos, and even recognize custom keywords. In this video, we are going to learn how to get started with the Google Speech-to-Text API in Python from scratch. I will show you every single step from create a Google Cloud project all the way to writing a Python script to connect to Google Cloud Speech-To-Text API. So if you are new to Google Cloud service, this would be a great introductory video to learn how to get started.
📑 Google Speech-To-Text Models: cloud.google.com/speech-to-te...
📑 Audio Encoding List: cloud.google.com/speech-to-te...
📑 Google Speech-To-Text API Reference: cloud.google.com/speech-to-te...
► Buy Me a Coffee? Your support is much appreciated!
-------------------------------------------------------------------------------------------
☕ Paypal: www.paypal.me/jiejenn/5
☕ Venmo: @Jie-Jenn
💸 Join Robinhood with my link and we'll both get a free stock: bit.ly/3iWr7LC
► Support my channel so I can continue making free contents
---------------------------------------------------------------------------------------------------------------
🛒 By shopping on Amazon → amzn.to/2JkGeMD
👩‍💻 Follow me on Linked: / jiejenn
🌳 Becoming a Patreon supporter: / jiejenn
✉️ Business Inquiring: [e-mail]
00:00 - Intro
00:50 - Google Speech-To-Text API Pricing
01:11 - Create Python Virtual Environment
03:17 - Install Speech-To-Text API Python package
03:36 - Create a Google Cloud project
04:50 - Enable Speech-To-Text API
06:38 - Create a Google Service Account
07:38 - Download Service Account client file
08:57 - Python script example 1 (local file)
17:47 - Python script example 2 (cloud storage)
#googlecloud #googlespeechtotext #googleapi

[@frankking5326]

After two days fighting with this on my own, your video solved my problem!! Thanks

[@mariodevelopersantos1102]

this is exactly what I needed, thanks

[@ashishkumar-eo1tz]

Simply awesome. Keep up the good work bro 👍

[@TheCloudShepherd]

Excellent. Thank you very much

[@RicardoCrumbleton]

How could this be adapted for the v2 api with Chirp?

[@DungLe-rp5vu]

Your instructions are great, besides how can I get text from online mp3 link?

[@user-wr4yl7tx3w]

by chance, do you have any idea what Industry Coding Assessment is, as part of an interview? I was told that it is not the same as testing you on algorithms, like in LeetCode.

[@jiejenn]

Each company is different, so there's no defined answer to be honest.

[@g_30_sanketpatil62]

hey bro i have created a voice bot using google dialogflow cx, now I wanted to transcribe the ongoing voice call so can you please tell me how can I achieve it
thanks

[@aastharathod8786]

how can i get it for JAVA?

[@user-wo2xo4du2l]

Donde se encuentra la interfaz de usuario?

[@ashishprakash8430]

hii, i follow your tutorial but it is not transcribing all audio.. please help.

[@frankking5326]

what error did you get?

[@ashishprakash8430]

@@frankking5326 found the solution, I was using default model. Video model worked. Thanks for your tutorial.

[@jubileudasilva9258]

Speech-to-Text has three main methods to perform speech recognition. These are listed below:
Synchronous Recognition (REST and gRPC) sends audio data to the Speech-to-Text API, performs recognition on that data, and returns results after all audio has been processed. Synchronous recognition requests are limited to audio data of 1 minute or less in duration.
Asynchronous Recognition (REST and gRPC) sends audio data to the Speech-to-Text API and initiates a Long Running Operation. Using this operation, you can periodically poll for recognition results. Use asynchronous requests for audio data of any duration up to 480 minutes.
Streaming Recognition (gRPC only) performs recognition on audio data provided within a gRPC bi-directional stream. Streaming requests are designed for real-time recognition purposes, such as capturing live audio from a microphone. Streaming recognition provides interim results while audio is being captured, allowing result to appear, for example, while a user is still speaking.

[@dhoreys]

My .wav file did not convert. Is there a sample .wav file I could use?

[@jiejenn]

You can search on Google, there are plenty.

[@dhoreys]

@@jiejenn The samples I have aren't working. I tried those. Gemini is saying to make sure that the file is in LINEAR16 format.

[@user-kb6ck7gb6f]

Is it possible to make it recognize in real-time from a microphone with good performance?
Edit: Another Question: Does it support the Arabic language as AWS doesn't in streaming (real-time)?

[@jiejenn]

Yeah, it definitely possible, but not going to be cheap though.

[@madhav1527]

Hi Did you find out a solution on how to get the input from a microphone, and supporting arabic? in real time, if so do let me know as i am having trouble in implementing the same

[@user-kb6ck7gb6f]

@@madhav1527 I used Open AI Whisper

[@madhav1527]

​@@user-kb6ck7gb6f but that has a cost right per api call, could you let me know if you found any library that does it without a cost

[@madhav1527]

​​@@user-kb6ck7gb6f and one more question, how accurate would you say the open ai whisper is

[@TheCloudShepherd]

Google documentation sucks. Thanks for this clearly explained how-to video

[@jiejenn]

Glad the video helped.

[@sadamhussain816]

Is it free?

[@manualdevalor]

No

[@7BlackJack8]

Google couldn't do any better to gets developer away from this. It's an atrocious mess to use the apis