Table of Contents

1. Challenge

   Enable the Cloud Text-to-Speech API

   1. From the Google Cloud console's main navigation, choose APIs & Services > Library.
   2. Search for "text", and select Cloud Text-to-Speech API.
   3. If necessary, click Enable.
2. Challenge

   Set Up Service Account

   1. Click Launch Editor.

   2. In the Shell Editor, expand the ai-conversations folder.

   3. Choose File > New File and name the file key.json.

   4. From this Hands-On Lab Credentials, copy the Service Account Credentials.

   5. Paste the clipboard contents into the new file, and choose File > Save.

   6. Switch to the Terminal enter the following command:

      export GOOGLE_APPLICATION_CREDENTIALS=key.json
      

3. Challenge

   Retrieve Working Files

   1. Activate the Cloud Shell.

   2. Retrieve the working files:

      git clone https://github.com/linuxacademy/content-gc-ai-services-deepdive
      

   3. In the Cloud Shell, change directories:

      cd content-gc-ai-services-deepdive/ai-conversations/
      

4. Challenge

   Send Request to Cloud Text-to-Speech API

   1. Call the Cloud Text-to-Speech API:

      curl -X POST 
      -H "Authorization: Bearer "$(gcloud auth application-default print-access-token) 
      -H "Content-Type: application/json; charset=utf-8" 
      -d @text-to-speech-request.json 
      https://texttospeech.googleapis.com/v1/text:synthesize 
      > synthesize-text.txt 
      

   2. In the Shell Editor, open synthesize-text.txt.

   3. Remove the following from the beginning of the file:

      {
        "audioContent": "
      

   4. From the end of the file, remove the following:

      "
      }
      

   5. Save the file.

5. Challenge

   Convert Response to MP3

   1. In the Cloud Shell, enter the following command:

      base64 synthesize-text.txt -d > synthesized-audio.mp3
      

   2. Download the MP3 file to your system:

      cloudshell download synthesized-audio.mp3
      

   3. Click Download.

   4. Open the downloaded MP3 file to hear the results.