New Input Reader

Vladimir Nikolić
Vladimir Nikolić
  • Updated

The New Input Reader combines functionalities of several modules:

  • Input Reader
  • Simple Menu
  • Speech to Text (STT)
  • Switch Node

Let's review the capabilities in more detail.

1. Settings

Here you can define what and how the customer can interact with this module.

In detail:

  • Input type
    • STT (Speech to Text - only spoken input) - the customer interacts only via voice
    • DTMF (only key pad input) - the customer interacts only via the keypad of his phone
    • STT and DTMF - the customer can use the keypad or interact via voice
      • DTMF will overwrite voice input
  • Voice bot provider - at the moment, we only offer one provider, however, the list will increase over time
    • Azure
  • Language
    • Select a wide variety of languages. This ensures that the voicebot correctly identifies the spoken words of the customer
  • Template 
    • Based on your specific requirements, you can select the following templates
      • Numeric - optimized for numeric entries (like the customer ID)
      • Confirmation - returns true or false depending on on either a confirmation or a denial (accounting for variations)
  • Accept only number input 
    • Useful, if you only want the module to store numbers, so any other words will be removed from it.
  • Pattern (regular expression) 
    • For more specific requirements, e.g. accepting only customer IDs which start with a 7, use this pattern. Check this article for details.
  • Allow to barge in
    • If enabled, the customer can interrupt the audio message 
  • Time to give initial input
    • How long the customer has time (in seconds) to either speak or press a button
  • Time to give input in between
    • How long the customer has time (in seconds) to either speak or press a button between inputs. For example, if the customer has to enter his customer ID, this defines the maximum time the customer has in between each entered number. A longer wait time is beneficial in fields where the entry may take time (like a customer ID).
Settings.png

 

2. Routing

Here you can define what should happen based on the customer input. You can also define more complex logics, using the advanced rule.

  • Simple rule
    • Define what happens if the customer enters a number 0-9 or the entry is true or false. You can define to what module the customer is routed.
    • In the screenshot the simple rule is: customer enters 1 = direct him to End Queue announcement
  • Advanced rule
    • Here you can use triggers and complex routing logics, which allow for higher flexibility.
    • In the screenshot the advanced rule is a trigger: Should a call start with 49, and the customer pressed 2, route the customer to Test ACD.
    • Advanced routing rules can replace a switch node following the input
Routing.png

 

3. Audio

You can define here:

  • Input audio
    • What audio is played to the customer when entering this module
    • The audio can be either coming from an audio file or a TTS (Text to speech)
  • Input retries
    • Here you could define what should be played after the customer has entered no input or the input was incorrect
    • You can granularly define what should be played to the customer if there was no input the first and second try, or the input was incorrect, therefore guiding the customer through the process
Audio.png

 

4. Automations

Here you can define what automations should fire if certain events are met.

The automations can be a:

  • Pre-automation
    • Starts the moment the customer enters this module
  • Post-automation
    • Starts the moment the customer is at the end of the module
  • No-Match-automation
    • Starts if the customer has provided incorrect data (e.g. customer ID does not start with a 7)
  • No-Input-automation
    • Starts if the customer has not provided any input
Automations.png

 


Note 1: There are some smaller known limitations with the New Input Reader which will be solved over time. Please refer to the status page for details on it.

Note 2: The Speech to Text (STT) and Text-to-Speech (TTS) features will incur additional third-party costs. These charges are determined by the duration of the caller's input and the pricing.
For detailed pricing information or assistance with cost estimation, please contact our support team at support@babelforce.com.

Related to

Was this article helpful?

/

Comments

0 comments

Please sign in to leave a comment.