Skip to content
This repository has been archived by the owner on Jul 22, 2024. It is now read-only.

Home

Jump to bottom
balajikadambi edited this page Jun 16, 2021 · 4 revisions

Short Title

Create a conversational Voicebot on WhatsApp with Watson services

Long Title

Build a framework that allows user to interact with a bot with voice using WhatsApp and Watson Services.

Author

URLs

Github repo

https://github.com/IBM/voicebot-on-whatsapp-using-watson-services

Summary

In this code pattern, We will build a framework using which the user will be able send queries over voice on WhatsApp and get a response from Watson Assistant. The query from the user is sent to the Watson Speech to Text service through a custom application. The output from the Watson Speech to Text service is then feed to Watson Assistant. Watson Assistant responds back to the user with an appropriate answer.

Technologies

Description

Conversational AI VoiceBots are helping businesses automate repetitive and time-consuming queries. This gives your team more time to tackle more complex, high priority strategic tasks, while still ensuring that the customers are engaged. Voicebots take in voice input can ingest, analyze, interpret, and respond to customer inquiries, with the end goal of either being able to answer a customer’s question in real-time or being able to continue a textual exchange with the customer to clarify the question at hand.

A Voicebot is useful in many scenarios where typing is not a convenient option:

  • Elderly customers find it more convenient to speak than to type. Some customers have better spoken language skills than written language skills. They find it easier to use VoiceBots.
  • Delivery executives on the move with a need to update systems.

In this code pattern, you will look a scenario of a customer speaking Brazilian Portuguese interact with a customer care center using WhatsApp. A framework is built using which the user will be able send queries using speech on WhatsApp, and then get a response from Watson Assistant. The query from the user is sent to the Watson Speech to Text service through a custom application. The output from the Watson Speech to Text service is then fed into Watson Assistant. Watson Assistant understands the query with the help of the built-in support for Brazilian Portuguese and responds back to the user with an appropriate reply.

When you have completed this code pattern, you will understand how to:

  • Use Watson Speech to Text service.
  • Use Watson Assistant service.
  • Integrate WhatsApp with Watson services.
  • Handle queries sent over voice on WhatsApp.

This code pattern can be configured to support multiple languages. Watson Assistant supports the following languages.

Flow

architecture

  1. User sends a voice or text message in WhatsApp.
  2. The message is redirected to Twilio Programmable messaging service.
  3. Twilio redirects the message to the Voicebot Application deployed on IBM Cloud or OpenShift.
  4. If the user has sent a voice message, the Voicebot Application leverages Watson Speech to Text to transcribe the message into text.
  5. The text message is sent to Watson Assistant.
  6. Watson Assistant chatbot detects the intent and replies with response accordingly.
  7. The Voicebot Application triggers the Twilio Programmable messaging service with the response message.
  8. Twilio Programmable messaging service redirects the response message to WhatsApp.
  9. User will be able to view the response message on Whatsapp.

Instructions

Find the detailed steps in the README file.

  1. Clone the repo
  2. Create Watson Services
  3. Create Twilio service
  4. Build and Deploy the Voicebot Application
  5. Configure Voicebot Application
  6. Try out voicebot on WhatsApp

Components and services

Clone this wiki locally