An Introduction To IBM Voice Agent With Watson

This Is A Guide To Create Your Own Virtual Voice Agent

Cobus Greyling
4 min readMar 31, 2020

--

Introduction

The logical progression of a chatbot is to interact with it via voice. To place a call to your bot and have a natural conversation like you would with a friend, or with a service representative.

There are a few commercial options available to you…one of them being IBM Voice Agent with Watson. This approach affords you easy configuration of your service, with no coding required.

It also allows you to assign a telephone number to the voicebot. Thus allowing you to call your voicebot and interacting with it, making for a neat demo.

The Essentials

You will need a twilio and IBM Cloud account to create your first VoiceBot. On twilio select the Elastic SIP Trunking option to add your Watson SIP address and also reserve a number.

IBM Voice Agent with Watson & twilio

The video above takes you through the basic of setting up a VoiceBot with IBM Voice Gateway.

Four Step Setup Within IBM Cloud

Within Voice Agent with Watson there is a four step process to launch your voice bot into the wild.

When creating a voice agent, Watson Voice Agent automatically searches for any available Watson service instances you can use in creating your voice agent. This is a very useful feature and can save you cost.

Certain plans also allows for a certain amount of instances, and reusing existing instances of TTS, STT etc. can save resources.

If no service instance is available, you can create one along with the voice agent or connect to services in a different IBM Cloud account.

It is also possible to use other could elements like Google Speech to Text, or Google Text to Speech instance.

IBM Cloud Configuration

On your dashboard, go to the Voice agents tab and click Create a Voice Agent.

Select Voice when you need to choose the agent type.

IBM Watson Voice Agent with Tone Analyzer

For Name, specify a unique name for your voice agent. As you might have a list of services, choose a descriptive name. Also consider adding the region in which your services are. This will come in handy later. The name can be up to 64 characters.

For Phone number, add the number from your SIP trunk, including the country and area codes. The phone number can have a maximum of 30 characters, including spaces and + ( ) — characters. I successfully set up a South African number using Twilio. Choosing a local number based on your location saves money when it comes to demo time; and also while testing from a phone.

Virtual Voice Agent with Language Translator

You can add multiple numbers to one Voice Agent by clicking Manage, next to Phone Number.

To enable call transfer, enter the termination URI for your Default transfer target.

Under Conversation, configure the connection to your Watson Assistant service instance by clicking Location 1 or Location 2 and enabling the location that you selected.

You can use Watson Assistant service instances in IBM Cloud accounts that you or someone else owns. You can also connect to any of these options through a service orchestration engine.

Basic Virtual Voice Agent Demonstration

The Watson Assistant portion of you solution holds the logic, dialog, intents and entities.

Most of your programming, logic and general Voice Agent behavior is determined here.

Under Text to Speech, review the default configuration for your Text to Speech service instance by clicking Location 1 or Location 2 and enabling that location. You can customize your configuration with the following.

Conclusion

The real power of making your VoiceBot interactive and adding logic to it lies within the Watson Assistant component of hour VoiceBot. The Watson Assistant portion allows you to test your logic, session variables, intents and entities within the test pane.

You can also share a link for others to test the functionality, but in text. In a followup article I will discuss a few advance options.

--

--

Cobus Greyling

I explore and write about all things at the intersection of AI & language; LLMs/NLP/NLU, Chat/Voicebots, CCAI. www.cobusgreyling.com