Page tree
Skip to end of metadata
Go to start of metadata

Text-to-speech is an inbound behavior action that processes written text prompts into audio announcements. Text-to-speech is an excellent option for auto-attendants (menus), especially ones that require regular updates.


Step-by-step guide

To use text-to-speech in an auto-attendant (menu):

  1. In the control panel, click Extensions in the main menu. On the Extensions page select the desired extension to edit from the list.
  2. Click Edit in the Inbound Behavior section.  
  3. Click the drop-down box next to Step #1 and select Text to Speech.
  4. In the provided text field enter your desired text.
  5. Use the drop-down list next to Voice to select the voice style.  
  6. Click Submit to save.


Best Use Practices

  • When using the text-to-speech function in an auto-attendant (menu), it is recommended to add a Step #2 action of Wait for 2-4 seconds to provide extra time for the caller to select an option. If no wait or terminating action (denoted by an *) is in the steps, the menu audio will repeat 3 times before hanging up.
  • Be sure to enable the  "Allow caller to input a menu option during the above steps" and select actions to match your text-to-speach script.
  • Place a test call to the new extension to confirm the pronunciation of your script. Text-to-speech often can mispronounce proper names or text with hyphens or apostrophes and your script may need to be adjusted.
  • The text-to-speech option can not be used as an action for the button input options. To use the text-to-speech option within a menu for a specific input, create a new virtual extension and build the text-to-speech function in the new extension. Once the new extension is completed, use the action Transfer to Extensions to send the specific input to the newly created extension.