Set Up a Voice-Enabled Text Virtual Agent

Follow the steps on this page to voice-enable a text virtual agent.

Prerequisites

To use a text virtual agent with voice channelsClosed A way for contacts to interact with agents or bots. A channel can be voice, email, chat, social media, and so on., you must have: 

Add an App to Virtual Agent Hub

Required permissions: Automation & AI > Launch Automation & AI

Adding a configuration app to Virtual Agent Hub establishes the connection between CXone Mpower and your virtual agent provider.

  1. In CXone Mpower, click the app selector and select Other > Automation & AI and then click Virtual Agent Hub. You can also double-click the virtual agent action in your Studio script to launch Virtual Agent Hub.
  2. Click Add Bot.

  3. Enter a Virtual Agent (Bot) Name and click in the list of virtual agent providers.

  4. Click Next.

  5. Complete the fields in the configuration form and click Next. You can find details about this form in the Configuration Page Details section on this page.

  6. Click Next.

  7. On the Voice page, select Text Only (No Voice Support) on the Voice page.

  8. Click Next.

  9. On the Transcript page, select the option for whether you want the conversation transcript and intent information captured. If this tab is not available, the feature is not enabled for your tenantClosed High-level organizational grouping used to manage technical support, billing, and global settings for your CXone Mpower environment. Contact your Account Representative for more information about this feature.

    Option Details
    Intent information only

    Select this option if you want to want to capture intent information only. Captured data is stored only for the duration of the interaction by default.

    This option requires custom scripting.

    Nothing Select this option if you don't want to capture conversation transcriptions or intentClosed The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish information.
    Transcript and intent information

    Select this option if you want to capture both transcript and intent data. Captured data is only stored for the duration of the interaction by default.

    This option requires custom scripting.

    Transcript only Select this option if you want to capture transcript information only. Captured data is stored only for the duration of the interaction by default.

    This option requires custom scripting.

  10. Click Next.

  11. On the Test + Add page, you can test your bot's connection by sending voice or text prompts. If your test messages don't work, click Back to return to the Configuration page and verify the settings.

  12. Click Add.

Configuration Page Details

Complete the Configuration page for the virtual agent you're voice-enabling. Refer to the details table on the integration setup page for your virtual agent provider: 

For some of these virtual agents, the original voice implementation was offered via SIP backchannel connection only. The method described on this page is another option to voice-enable a text virtual.

Create a Script

Required permissions: Studio Script View, Create/Edit

To voice-enable a text virtual agent, your script should: 

  • Have the phone media typeClosed A medium, such as voice, email, and chat, through which a contact connects with an intended recipient..
  • Use the Voicebot Exchange action. Your script must include at least two instances of this action. When configuring these actions:
    • Configure both instances with virtualAgentID set to the Virtual Agent Hub profile you created for your bot. If your script has more than two instances of the action, they all must be configured to use the same profile.
    • In the first instance of the action that appears in the script, ensure that the botSessionState property is empty.
    • Copy the configured value of botSessionStateVar from the first instance of Voicebot Exchange.
    • In the second instance of the action, paste the value you copied from botSessionStateVar in the preceding bullet step into the botSessionState property.

  • Have a CLOUD TTS action near the beginning of your script. Configure CLOUD TTS with your TTS provider and the voice and language you want it to use when responding to contacts. Alternatively, you can use the TTS service in the PLAY action with a VOICEPARAMS action to choose the voice.

    Including Cloud TTS or PLAY with VOICE PARAMS is only required if you want to change the voice or language of the synthesized voice. If you want to use the default Studio TTS voice, you can omit these actions.

  • Have a CONTINUOUS TRANSCRIPTION action before the first VOICEBOT EXCHANGE action. Ensure that: 
    • Transcription Profile is set to the profile you want to use with this bot. If the profile you want doesn't exist yet, you can create it.
    • Enabled is set to True.
    • Participants is set to Patron.
    • Generate Utterance Events is set to True.
  • In your Default Next Prompt Behaviorssnippet, add the following parameters:
    • enableSpeakerBarge="true"
    • useContinuousTrancription ="1"
    • bargeOnUtteranceBeginRatherThanEnd="1"

    Do not modify these parameters in any Next Prompt Behaviors snippets in this script.

The following images show an example script for voice-enabling a text virtual agent. The first image is a Studio script and the second is for Desktop Studio. You can download these scripts.

Image of a script with the TTS VOICE and CONTINUOUS TRANSCRIPTION actions.

Image of a script with the TTS VOICE and CONTINUOUS TRANSCRIPTION actions.

Note that these are not complete scripts. You may need additional work to complete the script for your organization. In this script, the CLOUD TTS and CONTINUOUS TRANSCRIPTION actions are located near the beginning of the script, along with the Default Next Prompt Behaviors snippet. This means they affect the entire conversion between the virtual agent and the contact.

You may want to add a branch to handle escalation to a live agent. If you want to stop transcription, include another CONTINUOUS TRANSCRIPTION action and set the Enabled property to False. If you need transcription to continue after the live agent answers the call, you don't need to do this.

You need at least one Studio script to route interactions to your virtual agent. Follow the .

You can learn more about Studio scripting in the Fundamentals and Technical Reference Guide sections of the online help.

When your virtual agent is ready to go into production, assign the script to one or more points of contact.

Assign the New Virtual Agent App to an Action

Required permissions: Studio Script View, Create/Edit

When the virtual agentClosed The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish app is set up and configured in Virtual Agent Hub, you need to assign it to the virtual agent action in your script. This connects the action and the script to your virtual agent provider.

  1. In Studio, open the script you want to modify.

  2. If you haven't done so already, click the Tools tab, expand the Automation and AI category, and add the virtual agent action you want to use. Be sure to put it in the correct location in your script. If you don't see the action you expect, verify that your script media type is correct. For example, if you're creating a script for a voice virtual agent, the script must be a phone script.

  3. Double-click the action to open Virtual Agent Hub.

    The Virtual Agent Hub main page has a list of current bots is on the left. Each has a delete icon and a checkmark icon to the right of the bot name.

  4. In the left column, locate the virtual agent that you want to assign to the action and click the checkmark An icon of a circle with a checkmark inside. next to it.

    An alternative to using the checkmark is to create a variable in your Studio script. Use the variable to pass the virtual agent app name into the Virtual Agent ID property of the Virtual Agent Hub action you're using.

  5. Click Close.

Test Your Virtual Agent

Required permissions: Automation & AI > Launch Automation & AI

You can test many aspects of your virtual agent to make sure everything works as intended. You can run tests from the virtual agent app's properties page in Virtual Agent Hub. When testing, you can: 

  • Verify that the virtual agent app is correctly configured to communicate with the virtual agent provider.
  • Add custom payload JSON to test the virtual agent's handling of custom payload data.
  • Trigger a welcome intent event to test how the virtual agent begins a conversation.
  • Trigger a custom intent event to test any custom events you've created for your virtual agent.
  • Trigger a timeout event to test how the virtual agent responds when the contact times out.
  • Test how the virtual agent handles DTMFClosed Signaling tones that are generated when a user presses or taps a key on their telephone keypad. input.

The following image is an example of the properties page for a virtual agent app in Virtual Agent Hub. It shows the Configuration and Voice tabs and the Test pane.

The properties page for a bot in Virtual Agent Hub showing the Test pane on the right side of the page.

  1. In CXone Mpower, click the app selector and select Other > Automation & AI and then click Virtual Agent Hub. You can also double-click the virtual agent action in your Studio script to launch Virtual Agent Hub.
  2. Click to select the configuration app for the virtual agent you want to test from the list on the left.

  3. In the Test pane, enter a test message in the Type a message field and press Enter to send it.

  4. Click Start with welcome intent to start a test conversation from the beginning. The virtual agent responds with its default welcome message. You can enter test messages.

  5. Click More Options An icon with three dots stacked vertically. to test other aspects of your virtual agent.

    Field Details
    Add Custom Payload JSON

    Select to test sending custom payload JSON to your virtual agent.

    Enter the custom payload in the Add Custom Payload JSON text box that appears on the Test + Add page. Press Enter after each line.

    Send a test message when you're ready to test the custom payload. When you're finished testing custom payload, click Close on the Add Custom Payload JSON pane.

    Trigger Welcome Intent Event Select to test the default Welcome intentClosed The meaning or purpose behind what a contact says/types; what the contact wants to communicate or accomplish. The virtual agent sends the welcome message. Enter a message to respond.
    Trigger Custom Intent Event Select to test a custom intent event. Enter the Event Name in the pop-up that appears and click Trigger. The virtual agent sends the message for the intent you entered. Send a response to test the intent.
    Trigger Timeout Event Select to view the default timeout intent. The virtual agent sends the timeout response message that it's configured with.
    DTMF Input Select to test your voice virtual agent's response to DTMFClosed Signaling tones that are generated when a user presses or taps a key on their telephone keypad. tones. Enter DTMF Characters and click Input to see the virtual agent's response to those characters.
  6. Click Reset to start your test again.

  7. If you need to make changes based on the results of your testing, you can: 

    • Modify the Studio scripts for the virtual agent.
    • Modify the configuration settings in the virtual agent's app in Virtual Agent Hub.
    • Modify the virtual agent's configuration settings in the provider's console. Click the large square button on the app properties page in Virtual Agent Hub. The example at the beginning of this section shows the Google Dialogflow CX app with the provider button. It has the An icon that has a square with an arrow overlaid on top of it. The arrow points from the center of the square to the top right corner of the square. icon on it to indicate that the link opens an external site.
  8. Test the virtual agent thoroughly after each change to your scripts or any configuration settings.
  9. When you're finished testing, click Close.