How can we help?

Talkdesk Guardian Identity: Configuring Voice Authentication and Voice Enrollment in Studio

Follow

Notes: Guardian Identity is Early Access; please reach out to your sales rep or Talkdesk Support for more information.

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 in to 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 Voice Enrollment components play an important role regarding voice collection and imprinting, and secure authentication.

These components need to be used together in the same Studio flow, but the Voice Authentication component should always be placed before the Voice Enrollment component. 

 

Configuring Voice Authentication and Voice Enrollment in Studio

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

VB_1.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 ID’s that can be used by callers include:  

  • Bank account number
  • Credit card number
  • Social Security Number
  • ID Card 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”.

VB_2.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.

 

Important Note: Please be aware that if the Voice Authentication component is used in the flow at this stage, but the contact still hasn’t enrolled into the feature, 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 and will only occur further ahead during the execution of the call flow. This component will only be properly executed if the caller enrolls in the feature. 

VB_3.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 is 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.

    • 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.
      • 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.

VB_4.png

5. Configure the Voice Authentication exits: 

    • Successful: In 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 in seconds, for this component, 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.

In case the contact is not enrolled, the voice authentication failed or if the call has timed out, we recommend you consider adding the Assignment and Dial component to the “Contact Not Enrolled” exit on the Voice Authentication component. This way, your agents can perform Knowledge Base Authentication (KBA) questions before allowing the contact to enroll in the feature. 

VB_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. Furthermore, the voice enrollment is triggered after a link is clicked on Callbar, the reason for which the Voice Enrollment component should be placed after the Assignment and Dial component on the “Call Finished” exit. By doing so, and by performing all the previous steps as described, the agent would be able to forward the contact to the enrollment step after hanging up the call. The caller would stay on the line and perform the necessary audio repetitions of the passphrase.VB_6.png

7. Configure the Audio message your contacts will hear and make sure that the instructions are clear. Choose one of the passphrases from the available options on the drop-down menu in your preferred language.

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”). You can use the variable {{passphrase}} in the Text-to-speech audio format. This passphrase variable refers to the one selected above, and on the Authentication component’s “Phrase” field. 

 

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, not to jeopardize the accuracy of the enrollment.

VB_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 are enough.

Note: for a 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 on Step 2. 


VB_9.png

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

VB_10.png

11. 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.  

12. Click Save 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

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

 

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