Speech service profiles

In the following, you will learn how to customize speech-to-text or text-to-speech profiles under Speech service profiles, depending on which provider you use. You can select different languages to represent which languages your profile supports.

In the following, you will learn how to create or delete a speech-to-text profile.

How to create a speech-to-text profile:

Requirement

  1. You have received the REST endpoint ID and subscription key from your speech-to-text service provider.
  1. In the navigation bar under Administration, click Speech service profiles.
  2. Under Speech-to-text profiles, click .
  3. Under Profile, select a Speech service.
  4. Enter a Profile Name.
  5. Select at least one language in Supported languages to express which languages are supported by the profile.
  6. Depending on the selected service, you can enter the (Service) Advanced settings.
  7. If you have selected Microsoft, make the following settings or enter the following data:
  8. If you want to activate streaming, slide the switch to Streaming enabled.
  9. If you want profanity to be censored with asterisks in the transcription results, slide the switch to Filter out profanity.
  10. Enter a REST endpoint ID.
  11. Choose an Azure region.
    Tip: If no region is specified, westeurope is used by default.
  12. Enter a Subscription key.

    Tip: If you do not enter a subscription key, the default VIER speech service profile is automatically used.
  13. If you want to specify phrases that should be recognized preferentially during transcription, enter them under Preferred phrases.

    Tip: Confirm each phrase entered with the Enter key.

    Tip: If you want to use phrases for specific sections in the dialog that should be recognized preferentially during transcription, you must specify them via the API endpoint /call/transcription/switch. For more information https://cognitivevoice.io/specs/#/call/switchTranscription.
  14. If you have selected Google, you can enable streaming by switching to Streaming enabled.
  15. If you want profanity to be censored with asterisks in the transcription results, slide the switch to Filter out profanity.
  16. If you want to specify phrases that should be recognized preferentially during transcription, enter them under Preferred phrases.

    Tip: Confirm each phrase entered with the Enter key.

    Tip: If you want to use phrases for specific sections in the dialog that should be recognized preferentially during transcription, you must specify them via the API endpoint /call/transcription/switch. For more information https://cognitivevoice.io/specs/#/call/switchTranscription.
  17. In Service account login data upload the JSON file you got when creating the service account at Google. This JSON file contains the credentials required for the integration with VIER Cognitive Voice Gateway.
  18. If you have selected IBM, make the following settings or enter the following data:
  19. If you want profanity to be censored with asterisks in the transcription results, slide the switch to Filter out profanity.
  20. Enter the Server URL you got from IBM.
  21. Enter the API key you got from IBM.
  22. Click Save.
  1. Your speech-to-text profile is saved.
  2. Speech service profiles - speech-to-text profile

How to delete a speech-to-text profile:

  1. In the navigation bar under Administration, click Speech service profiles.
  2. Select the speech-to-text profile you want to delete.
  3. Click Edit and click Delete.
  4. Click Confirm.
  1. Your speech-to-text profile has been deleted.

In the following, you will learn how to create or delete a text-to-speech profile.

In the following, you will learn how to create a text-to-speech profile. For this purpose, you will perform the following actions:

  • Enter basic data
  • Set up voice

Enter basic data

How to enter basic data:

  1. In the navigation bar under Administration, click Speech Service Profiles.
  2. Under Text-to-speech profiles, click .
  3. Select a Speech service under Profile.
  4. Enter a Profile name.
  1. You have entered basic data.

Set up voice

How to set up voice:

  1. Click .
  2. Under Voice, select at least one Language.
  3. Enter a Voice name used by provider.
  4. If you have chosen Google, you can enter the data of your Google service account under Google advanced settings.
  5. Enter your data directly under Service account login data or click Load login data from JSON file and choose the file containing the data.
  6. or
    If you have chosen Amazon, you can enter the data of your Amazon service account under Amazon Advanced settings.
  7. Enter the Access key ID.
  8. Enter the Secret access key.
  9. or
    If you have chosen Microsoft, you can enter the data of your Microsoft service account under Microsoft Advanced settings.
  10. Enter the REST endpoint URL.
  11. Enter the Authentication URL.
  12. Enter the Subscription key.
  13. or
    If you have chosen IBM, you can enter the data of your IBM service account under IBM Advanced settings.
  14. Enter the Server URL.
  15. Enter the API key.
  16. Click Save.
  1. You have set up voice.
  2. You have created a text-to-speech profile.
  3. Speech service profiles - text-to-speech profiles

How to delete a text-to-speech profile:

  1. In the navigation bar under Administration, click Speech service profiles.
  2. Select the text-to-speech profile you want to delete.
  3. Click Edit and click Delete.
  4. Click Confirm.
  1. Your text-to-speech profile has been deleted.