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 such as
<emphasis>to emphasise important parts<break time='400ms'>to add break after every sentence or before important informations
How to ask questions:
Scripts should be short and sweet
To the point and close ended questions
SSML
To get the best customer experience, the SSML should be properly written in order to have perfect pauses and breaks where needed.
Reference: https://cloud.google.com/text-to-speech/docs/ssml# and let the magic begin
One should avoid unnecessary tags while using SSML
DialogFlow Training
As important as the flow is the Intent Training
Create the required intents in Google DialogFlow or IBM Watson
Create lots of Entities!!
Reference:
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
Add Comment