How can we help?

Configuring Voice Authentication and Enroll Voice in Studio

Follow

These components have additional usage costs. For detailed information on their pricing, please contact your Customer Success Manager. Callers will only be enrolled if they explicitly opt into having their voice profile captured. At any time, during an interaction with a customer representative, callers can ask to trigger an opt-out, which will delete their respective voice profiles. Talkdesk recommends reaching out to your legal counsel about consent-based voice biometrics requirements, before setting up this functionality.

 

When a caller chooses to opt into the feature, the “Voice Authentication” and “Enroll voice” components play an important role regarding voice collection and imprinting, and secure authentication.

 

Configuring Voice Authentication and Enroll voice in Studio

To ensure that callers are securely authenticated, please configure your Studio flow as detailed below: 

image_2.png

1. After the initial step, you can choose to add an Input IVR component that will be used to collect the contact’s unique identifier, i.e., the Contact ID. 

The Contact ID is a personal and non-transferable number of which the caller is the sole holder and that will be used to perform a secure authentication every time the user calls in. Examples of Contact IDs that can be used by callers include:  

  • Bank account number.
  • Credit card number.
  • Social Security Number.
  • ID Card number.
  • Personal Phone Number. Any other set of digits that uniquely identifies the user calling in. 

The purpose of this Contact ID is to have a single voiceprint matching a single contact. If you choose not to set any “Input IVR” component to collect a unique identifier, the caller’s phone number can be used as the identifier. However, please bear in mind that a phone number is not a unique identifier, as it can be shared by many people (in the context of a company or a household, for example), thus compromising the efficiency of the authentication. 

In the example, the “Input IVR” is being used to collect the contact’s ID. Configure the Input IVR component according to your preferences and, in the end, set up the output variable from this component. In our example, we’ve named it “Contact_ID_Variable”.

image_1.png

2. Add a "Voice Authentication" component to the Input IVR exit for successful outcomes (exit “OK”) and fill in the remaining fields per your preferences.

 Note: Please be aware that if the “Voice Authentication” component is used in the flow at this stage, but if the contact hasn’t enrolled into the feature yet, the component will not fulfill its purpose, i.e., it will not serve to authenticate a caller, since the enrollment still hasn’t taken place. This component will only be properly executed if the caller enrolls in the feature.

 

image_4.png

3. On the “Voice Authentication” step, configure the audio message your contacts will hear.

You can use the variable {{passphrase}} in the text-to-speech audio format. This passphrase is the phrase that the contact uses to enroll, so for an accurate authentication, we advise that this passphrase be stated during the audio instructions in any of the available options (“Text-to-speech”, “Audio file upload” or “Other sources”).

 

Tip: Callers need to press a key on their keypads after saying the passphrase. That key is defined in the IVR component settings. Any key can be pressed to consider the authentication audios from the contacts. We advise you to include this reference in the audio instructions.

 

4. Configure the input and output variables that will store values to be used further down in the flow, or Callbar:

    • Input Variable: 
      • Contact ID: Caller’s unique identifier.

Tip: When using Conversations, there is no need to set up the Output variables.

    • Output variables:
      • auth status: Result of the caller’s authentication. This variable will return five different outputs, depending on the result of the authentication procedure:
          • “SUCCESS” - If the contact’s voice biometrics matches the contact’s voiceprint.
          • “FAILURE” - In case there’s no match of the voiceprint.
          • “ERROR” - If an error occurred.
          • “NOT_ENROLLED” - if the contact hasn’t been enrolled yet.
          • “TIMEOUT” - If the maximum waiting time is reached before the caller is able to authenticate.
          • NOT_CONSENTED - If the contact hasn’t yet consent to enroll yet.
          • NO_SPEECH - If the caller didn't speak.
          • UTTERANCE_FAILURE - If the caller tried to authenticate with a different passphrase from the one provided.
          • DEEP_FAKE - If the caller used a deep fake playback of a person's voice.
          • REPLAY_ATTACK - If the caller used a recording device to play back another person's voice.
      • start enrollment: A URL that will enable the agent to flag the call, which will trigger the enrollment component before the call is finished, depending on the configured flow. When the agent clicks on this button, a confirmation window will appear on a new browser tab for the agent to click on, thus validating the user’s intention to enroll. 
      • opt-out: A URL that will enable the agent to delete all the voice biometrics data from the caller. When the agent clicks on this button, a confirmation window will appear on a new browser tab for the agent to click on, thus validating the user’s intention to opt out.

image_3.png

5. Configure the "Voice Authentication" exits: 

    • Successful: n this section, you must select where to send the call if the voice authentication was successful, i.e. when the caller’s audio passphrase matched the contact ID voiceprint. You can, for instance, use a “Play Audio” component to notify your caller that the authentication was successful and then redirect the call to an automation-based component, such as “Virtual Agent”, that will handle the caller’s inquiries. 
    • No Match: Select where to send the call if the voice authentication failed, i.e. the caller’s audio did not match the contact ID voiceprint or an error occurred. Similarly, you can use a “Play Audio” component to let your caller know that the authentication was not successful. 
    • Contact not enrolled: Select where to send the call when the caller is still not yet enrolled into voice biometrics, i.e. the contact still doesn’t have a voiceprint created. You can also add a "Play Audio" component, for instance, to let your caller know that a voice authentication feature is available, or you can choose to add an Assignment and Dial step in order to have the caller speaking to an agent that will propose an opt-in to the feature.
    • Timeout: Configure the maximum time the system will wait for the caller to speak the passphrase, before redirecting the call to the next component in the flow. Please consider that the Timeout clock is in seconds, for this component, and starts when the audio instructions start; thus we advise you to take into account the length of the audio together with a period for the contact to speak the passphrase before setting the timeout component exit.
    • Error handling: This section is available in most Studio components. You can use it to define the behavior for unexpected failure during the execution of a component. For more information on this section, please refer to the "Error handling" documentation.

If the contact is not enrolled, the voice authentication failed or if the call has timed out, we recommend you consider adding, to those exits, the “Assignment and Dial” component. This way, your agents can perform Knowledge Base Authentication (KBA) questions at any point.

image_5.png

6. After the exits have been configured, the call should be routed to an agent, so that relevant Knowledge Base questions are performed to ensure the identity of the contact person.

In this flow, the Enroll voice component was placed after the “Assignment and Dial” component, on the “Call Finished” exit. Therefore, the agent will be able to perform some KBA questions and ask the caller’s consent to enroll. After the agent hangs up the call, the caller will remain on the line and start the enrollment process.

image_6.png

7. First, you need to choose if you are either going to use a predefined passphrase or a custom one. The main differences are explained in this article here. Afterward, configure the Audio message your contacts will hear and make sure that the instructions are clear.

To ensure a successful enrollment, the passphrase used for enrollment should be stated during the audio instructions in any of the available options (“Text-to-speech”, “Audio file upload”, or “Other sources”). If you have chosen the Predefined passphrase, then you can use the variable {{passphrase}} in the Text-to-speech audio format.

 

Tip: The contacts need to press a key from their keypads after stating the passphrase. That key is defined in the Studio component settings. Any key can be pressed to consider the enrollment audios from the contacts. We advise you to include this reference in the audio instructions, as well as a recommendation for the caller to utter the passphrase only when the instructions are over, as not to jeopardize the accuracy of the enrollment.

image_7.png

8. Set up the passphrase confirmation. This second audio message is aimed at instructing the contacts that a new audio segment is needed for the enrollment to be completed. This audio message will be repeated until the number of required passphrase repetitions is enough.


Note: For successful enrollment, the number of passphrase repetitions that contacts have to state may vary between two and five, depending on some factors (audio quality, passphrase wording, background noise, etc.).

9. Configure the Contact ID variable as an input variable. This should be the same variable you defined as the Contact ID in Step 2. 

image_8.png

10. Set up the “Voice Enrollment” exits, depending on the flow you would like to define.

image_9.png

11. If your agents are using Callbar, when finished configuring your flow, click on the Manage Context button and check the newly created variables, so they can be displayed in Callbar. If these variables aren’t checked, the agent will not be shown the authentication status nor the links to enroll and opt-out, thus rendering inoperable the ability to forget and enroll new users. 

If your agents are using Conversations, this step is not necessary, since the Identity tab in Conversations is already ready for these functionalities. To know how it all works in the Identity tab, read the following article.     

12. Click Save and then Publish, to complete the process. 


Visualizing Callbar Variables and Agent’s Actions in Callbar

1. Callbar displays the following information to the agent: 

  • The "authentication status" [1].
  • The Opt-out option [2].
  • The Start Enrollment link [3].

While ringing: 

VB_11.png

On a call: 

VB_11_not_enrolled.png

2. Since the authentication status field states that the contact is “Not enrolled” [1], after performing the necessary Knowledge Base authentication questions and collecting the contact’s consent, the agent would have to click on the Start Enrollment link [3] so that after the agent hangs up, the caller stays on the line and performs the enrollment process.

3. If the Agent doesn’t click on the Start Enrollment link [3], i.e. if the caller didn’t give the consent to use voice biometrics when the agent hangs up, the call will follow the flow’s pre-configured call path.  

Note: These steps assume that the "Voice Enrollment" component exits are configured as in our example above.

 

 4. When the authentication is successful, the “authentication status” field in the agent’s Callbar will have the following appearance. 

 

While ringing: 

VB_13.png

On a call: 

VB_15.png

5. When the contact calls and the authentication has failed, the “authentication status” field would display the following information on the agent’s Callbar.

 

While ringing: 

VB_16.png

On a call:

VB_17.png

 

Conversations app

When an agent is using the Conversations app, they can see a tab called Identity that is shown automatically to all agents during all inbound calls.

The agents can see real-time information regarding the authentication of callers with voice biometrics and fraud-related insights concerning the caller’s phone number.

This article shows an overview of the Identity tab functionalities.

If you need additional information on how to configure Identity on your Studio flow, please contact your Customer Success Manager or Talkdesk Support.

 

All Articles ""
Please sign in to submit a request.