Allows to generate an mp3 audio track of specified text. Uses Google Cloud service and need Google Cloud CLI

googlecloud-text-to-speech.sh

# export Google Credentials service account path
export GOOGLE_APPLICATION_CREDENTIALS=~/Keys/da-service-account.json

curl \
-vX POST https://texttospeech.googleapis.com/v1/text:synthesize \
-H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \  
-H "Content-Type: application/json; charset=utf-8" \
-d @ttsbody.json > synthesize-text.txt  # specify your json file

# get response and encode as mp3
cat synthesize-text.txt | grep 'audioContent' | \
sed 's|audioContent| |' | tr -d '\n ":{},' > tmp.txt && \
base64 tmp.txt --decode > synthesize-text-audio.mp3 && \
rm synthesize-text.txt \
rm tmp.txt

ttsbody.json

{
  "audioConfig": {
    "audioEncoding": "mp3",
    "effectsProfileId": [
      "small-bluetooth-speaker-class-device"
    ],
    "pitch": 0,
    "speakingRate": 1
  },
  "input": {
    "text": "Benvenuto in Delivery Aggregator! Premi \"uno\" per ricevere assistenza tecnica, premi \"due\" per ricevere assistenza commerciale oppure premi \"tre\" per ricevere assistenza amministrativa."
  },
  "voice": {
    "languageCode": "it-IT",
    "name": "it-IT-Wavenet-A"
  }
}