net - UK (2020-04)

PROJECTS
Text-to-Speech API

STEP 5:6(77+((19,5210(17

9$5,$%/(

The private key file needs to be used to authenticate

you when calls are made to the API. To make this

easy, set the GOOGLE_APPLICATION_CREDENTIALS

environmental variable to point to your JSON file you

just downloaded.

Open a new terminal window on your computer

and use the export command like this:

export GOOGLE_APPLICATION_CREDENTIALS=“/[path to

file]/[file name].json”

Mine looked like this, for example:

export GOOGLE_APPLICATION_CREDENTIALS=”/Library/

WebServer/Documents/net-text-to-speech/Text To

Speech-bc489c0a7499.json”

Be sure the path is correct to the place you stored

the private key file. Replace the [file name] with your

private key file and use the path to your file.

On Windows, you can do the same thing via the

command line, like this:

$env:GOOGLE_APPLICATION_CREDENTIALS=“C:\[path to

file]\[FILE_NAME].json”

If you close your terminal or console window, you

may need to run that command again. We’ll add this

into our server-side code shortly as well, so you don’t

have to worry about it again.

STEP 6:0$.($1$3,5(48(67

86,1*&85/

Curl requests can be made in many languages

including PHP, Python and Node. This way you can

make the calls direct in command line or assign the

result to a variable in the language of your choice. If

you need some help using curl, visit this link here:

https://curl.haxx.se/.

Here is an example of a curl call to return MP3 data

of synthesised speech. You’ll notice the data we send

is comprised of three main nodes; input, voice and

audioConfig. We use the input to indicate the ‘text’ to

synthesise into speech, the voice to define how the

voice sounds and the audioConfig node to define the

data type we want to have returned.

curl -H “Authorization: Bearer “$(gcloud auth application-

default print-access-token) -H “Content-Type: application/

json; charset=utf-8” --data “{

‘input’:{

‘text’:’I’ve added the event to your calendar.’

},

‘voice’:{

‘languageCode’:’en-gb’,

‘name’:’en-GB-Standard-A’,

‘ssmlGender’:’FEMALE’

},

‘audioConfig’:{

‘audioEncoding’:’MP3’

}

}” “https://texttospeech.googleapis.com/v1/

text:synthesize”

This will return a JSON object with a property called

audioContent, which is in Base64 format. You’ll need

to decode this into an audio file to play it or process

this data as you prefer. For example, you could write

the data to a text file then run the decode command

like this:

base64 source_base64_text_file -d > dest_audio_file

This method is a couple of steps but gives you a lot

of flexibility in terms of the devices and platforms

you may wish to use.

Continue using this method to test out the calls

if you wish. Make curl calls from your app if your

language supports them. You can also set up a local

SDK in a language you prefer and integrate into your

app. That’s what we’ll look at next.

STEP 7:,167$//&/,(17/,%5$5<

Next we’re going to create a web-based app to

demonstrate how to integrate the API into your

projects. This is a lot easier to use than making

manual curl calls via command line.

There are a number of SDKs available in a variety

of languages. We’re going to use the PHP SDK. If

you want to adjust the code slightly and use another

language such as Node.js, there is a great resource

of SDKs here: https://cloud.google.com/text-to-speech/

docs/reference/libraries.

Start the process by making sure that you have a

project folder set up on your local or remote server.

If you don’t already have Composer, make sure

to set that up to install the SDK. If you don’t have

Above When creating a

service account, give a

name to your new service

and make sure to leave the

role unselected