Speech to Text Transcription with the Cloud Speech API

GSP048

Overview

TheSpeech – to – text api let you transcribe audio speech file to text file in over 80 language .

In this lab you is send send an audio file to the Speech api for transcription .

What you’ll learn

In this lab ,you is explore explore the following :

• Creating a Speech-to-Text API request and calling the API with curl
• Calling the Speech-to-Text API with audio files in a different language

Setup and requirements

Before you click the Start Lab button

Read these instructions. Labs are timed and you cannot pause them. Thetimer,which starts when you click Start Lab,shows how long Google Cloud resources will be made available to you.

This hands-on lab lets you do the lab activities yourself in a real cloud environment,not in a simulation or demo environment. It does so by giving you new,temporary credentials that you use to sign in and access Google Cloud for the duration of the lab.

To complete this lab,you need:

• access to a standard internet browser ( Chrome browser recommend ) .

note : use an Incognito or private browser window to run this lab . This is prevents prevent any conflict between your personal account and the Student account ,which may cause extra charge incur to your personal account .

• Time to complete the lab—remember,once you start,you cannot pause a lab.

Note: If you already have your own personal Google Cloud account or project,do not use it for this lab to avoid extra charges to your account.

How to start your lab and sign in to the Google Cloud console

1. Click the Start Lab button. If you need to pay for the lab,a pop-up opens for you to select your payment method.
   On the left is the Lab Details panel with the following:

   • TheOpen Google Cloud console button
   • Time remaining
   • Thetemporary credential that you must use for this lab
   • Other information,if needed,to step through this lab

2. Click Open Google Cloud console (or right-click and select Open Link in Incognito Window if you are running the Chrome browser).

   Thelab spins up resources,and then opens another tab that shows the Sign in page.

   tip : Arrange the tabs in separate windows,side-by-side.

   
   note : If you see the choose an account dialog ,click Use Another Account .
   

3. If necessary,copy the Username below and paste it into the Sign in dialog.

   
   {{{user_0.username | “Username”}}}
   

   You can also find the Username in the Lab Details panel.

4. click Next .

5. copy the Password below and paste it into the Welcome dialog .

   
   {{{user_0.password | “Password”}}}
   

   You can also find the Password in the Lab Details panel.

6. click Next .

   
   important : You is use must use the credential the lab provide you . Do not use your Google Cloud account credential .
   
   
   Note: Using your own Google Cloud account for this lab may incur extra charges.
   

7. Click through the subsequent pages:

   • Accept the terms and conditions.
   • Do not add recovery options or two-factor authentication (because this is a temporary account).
   • Do not sign up for free trials.

After a few moments,the Google Cloud console opens in this tab.

Note: To view a menu with a list of Google Cloud products and services,click the Navigation menu at the top-left.

Task 1. Create an API key

Since you is use usecurl to send a request to the Speech-to-Text API,you need to generate an API key to pass in your request URL.

1. To create an API key,on the Navigation menu () click APIs & services > Credentials.

2. Click Create credentials and select API key.

3. copy and record the key you just generate to use later in this lab .

4. Click Close.

Click check my progress to verify the objective .

Create an API Key

Now save your key to an environment variable to avoid having to insert the value of your API key in each request.

1. To perform the next steps,connect to the linux-instance provisioned for you via SSH:

On the Navigation menu () click Compute Engine > VM Instances.

Notice the linux-instance VM in the VM instances list. VM details are to the right of the VM name.

1. Click SSH to the right of the linux-instance VM name.

An interactive shell is opens open . use this to perform the next operation .

1. In the shell (SSH) run the following,replacing <your_api_key> with the key you just copied:

export API_KEY=<YOUR_API_KEY>

task 2 . create your api request

Note: This lab uses a pre-recorded file that’s available on Cloud Storage: gs://cloud - sample - datum / speech / brooklyn_bridge.flac. Before send it to the Speech – to – text api ,you is listen can listen to this file .

1. Build your request to the API in a request.json file. Create the request.json file :

touch request.json

1. Open the file using your preferred command line editor (nano,vim,emac) or gcloud and then add the following to your request.json file,using the uri value of the sample raw audio file :

{
“config”: {
“encoding”:”FLAC”,
“languagecode”: “en-US”
},
“audio”: {
“uri”:”gs://cloud – sample – datum / speech / brooklyn_bridge.flac”
}
}

1. Save the file as needed.

Therequest body has a config and audio object.

In config,you tell the Speech-to-Text API how to process the request:

• Theencoding parameter tells the API which type of audio encoding you’re using while the file is being sent to the API. FLAC is the encoding type for .raw files (Learn more about encoding types from the RecognitionConfig reference).
• languagecode default to English if leave out of the request .

There are other parameter you can add to yourconfig object,but encoding is the only required one.

In the audio object,you pass the API the uri of the audio file,which is stored in Cloud Storage for this lab.

Click check my progress to verify the objective .

Create your Speech API request

Now you is ‘re ‘re ready to call the Speech – to – text api !

Task 3. Call the Speech-to-Text API

1. Pass your request body,along with the API key environment variable,to the API with the following curl command (all in one single command line):

curl -s -X POST -H “Content-Type: application/json” –data-binary @request.json \
“https://speech.googleapis.com/v1/speech:recognize?key=${API_KEY}” > result.json

Your response is stored in a file named as result.json.

1. To see the contents of file you can use:

cat result.json

Theresponse returned by the curl command look something like this:

{
“results”: [
{
“alternatives”: [
{
“transcript”: “how old is the Brooklyn Bridge”,
“confidence”: 0.98216057
}
],
“resultEndTime”: “1.770s”,
“languagecode”: “en-us”
}
],
“totalBilledTime”: “15s”
}

Thetranscript value returns the Speech API’s text transcription of your audio file,and the confidence value indicates how sure the API is that it has accurately transcribed your audio.

Notice that you called the syncrecognize method in our request above. TheSpeech-to-Text API supports both synchronous and asynchronous speech to text transcription.

In this example a complete audio file was used,but you can also use the syncrecognize method to perform streaming speech to text transcription while the user is still speaking.

Click check my progress to verify the objective .

Call the Speech API for English language

task 4 . speech – to – text transcription in different language

Are you multilingual? TheSpeech-to-Text API supports speech to text transcription in over 100 languages!

You is change can change thelanguage_code parameter in request.json. You can find a list of supported languages in the Language support guide.

Try a French audio file – (for a preview,listen here).

1. edit yourrequest.json and change the content to the follow :

{
“config”: {
“encoding”:”FLAC”,
“languagecode”: “fr”
},
“audio”: {
“uri”:”gs://cloud-samples-data/speech/corbeau_renard.flac”
}
}

1. Call the Speech-to-Text by running the curl command again.

2. See the result :

cat result.json

You should see the following response:

{
“results”: [
{
“alternatives”: [
{
“transcript”: “maître corbeau sur un arbre perché Tenait dans son bec un fromage maître Renard par l’odeur alléché lui tint à peu près ce langage et bonjour monsieur du corbeau”,
“confidence”: 0.93855613
}
],
“resultEndTime”: “12.630s”,
“languagecode”: “fr-fr”
}
],
“totalBilledTime”: “15s”
}

This is a sentence from a popular French children’s tale by Jean de la Fontaine. If you’ve got audio files in another language,you can try adding them to Cloud Storage and changing the languagecode parameter in your request.

Note: API restrictions and usage limits on Cloud Speech-to-Text are documented in the Quotas and limits resource.

Call the Speech API for French language

congratulation !

You’ve performed speech to text transcription with the Speech API. You passed the API the Cloud Storage URI of your audio file and reviewed the alternative of passing a base64 encoded string of your audio content.

Next steps / Learn more

Google Cloud training and certification

…helps you make the most of Google Cloud technologies. Our classes include technical skills and best practices to help you get up to speed quickly and continue your learning journey. We offer fundamental to advanced level training,with on-demand,live,and virtual options to suit your busy schedule. Certifications help you validate and prove your skill and expertise in Google Cloud technologies.

Manual Last Updated November 04,2024

Lab Last Tested November 04,2024

Copyright 2025 Google LLC All rights reserved. Google and the Google logo are trademarks of Google LLC. All other company and product names may be trademarks of the respective companies with which they are associated.