Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

Want to create an Awesome Customer Experience Voice IVR?

Follow few basic steps and you are good to go….

Must Follow

  • Start with:

    • Add a connection delay. We recommend adding 500 ms to 1 sec delay. This delay will change based on Inbound or Outbound modes.

    • Start with Greetings, such as “Good Morning”

    • Add the customer name whenever possible, eg: “Good Morning Abhishek”

  • Script:

    • Use SSML Tags

  • Use SSML Tags such as

    • Go through all SSML Tags from here: https://cloud.google.com/text-to-speech/docs/ssml#

    • Use SSML Tags such as

      <emphasis> to emphasise important parts

    • <break time='500ms'> to add break after every sentence or before important informations. Keep time > 400ms at-least.

    • Use <s>...</s> tags to wrap full sentences, especially if they contain SSML elements that change prosody (that is, <audio>, <break>, <emphasis>, <par>, <prosody>, <say-as>, <seq>, and <sub>).

    • If a break in speech is intended to be long enough that you can hear it, use <s>...</s> tags and put that break between sentences.

  • How to ask questions:

    • Scripts should be short and sweet

    • To the point and close ended questions

  • DTMF options:

    • Always configure the “Length” of DTMF input to ensure that after correct. Most of the time you’ll be taking a 1 digit input (i.e. 1 to 9), so please ensure Length is set to 1.

    • Add pause after important bits, example: Press 1, for account information to add a delay after “Press 1”

      • Add break delay after each option for enough time for customer to process the information. We recommend <break time=”600ms”>

    • Always add an option to repeat the information.

  • SSML

    • To get the best customer experience, the SSML should be properly written in order to have perfect pauses and breaks where needed.

    • One should avoid unnecessary tags while using SSML

  • DialogFlow Training

  • Handle All Branches

    • Make sure one covers all the scenarios and branches of the widgets

  • Single Utterances

    • Single utterance is the function of Google which helps to identify single word inputs in a better way

    • Enabling single utterances is not a sure shot solution in case of languages other than Eng(US) as none of them have the phone call model by Google enabled for STT

    • One can enable single utterance and choose not to add any “Expected Phrases” if not needed

    • To know more check out the user manual /wiki/spaces/PD/pages/17137699

  • Expected Phrases

    • Class tokens as well as single utterance words, phrases can be added under expected phrases to let the system understand and better detect the speech

    • Make sure no “Space” is added between two expected phrases i.e. Correct → Yes,Yes this is correct and Wrong → Yes, Yes this is correct

    • To know more check out the user manual /wiki/spaces/PD/pages/17137699