Voice Assistants as a Service

How it works

The Slang CONVA platform is unique in the way it enables adding Voice Assistants to your app. Just like AWS enables adding new devices to your "lab" by making use of pre-built VMs, the Slang CONVA platform includes a set of pre-built, domain-specific Voice Assistants, that have been pre-trained and provides a simple way to connect these Assistants to apps belonging to those domains. The platform follows a "Batteries Included" approach and comes with

  • Pre-built, domain-specific Voice Assistants that have been trained and configured to support a well-defined set of user journeys. Every Assistant provides the following features Abstracts out the underlying deep tech components like Automatic Speech Recognition (ASR), Natural Language Understanding (NLU), and Text-to-speech (TTS) so that the integrators of the Assistant don't need to think in those low-level terms. Pre-trained to understand multiple, domain-specific user journeys along with domain-specific data catalogs (which could be optionally extended) Multi-lingual support out of the box for all the supported user journeys

    Rich UI components that can be embedded inside your app, that are necessary for interaction with the end-user. It also includes sub-components to help the user get on-boarded successfully and also helps them to get trained on what to speak and when to speak Conversational design constructs such as

    - Prompts, which are questions that the app needs to ask the end-user

    - Statements, which are things that the app wants to inform the user

  • Configuration options to customize the Assistants to suit the app's needs

  • Mobile and Web SDKs to allow the app and the Assistant to work together seamlessly

  • Authentication management

  • Accounting

The Slang In-App Voice Assistants require an internet connection to work. It talks to a highly scalable back-end that is optimized to provide sub-second responses to most user queries (depending on network latencies)

From a developer perspective, there are two main components involved:

  • The Slang CONVA Console - where you select, configure and manage the Assistant and also your account details

  • The Assistant SDK - which enables integration of the Assistant with the app through platform-specific programming interfaces

Next, let's dive deeper into the most important Assistant concepts.

Last updated