Voice+

Learn to set up a readymade Voice+ application with NLX in minutes

What's a readymade Voice+ application?

Choosing Voice+ when creating a new application is a fast, starter application that enables true two-way, hands-free conversations between a user and AI across web or mobile applications.

This application type turns your site or app into a voice-driven assistant that can talk, understand, and act, so your users accomplish goals more easily when visiting your domain.

Features
Readymade Voice+ app
Custom app with Voice+ node

UI navigation Move between pages

Fill forms Enter fields & correct field entries

Use real-time context SDK analyzes pages to improve navigation and forms

Trigger commands Send structured data to your frontend

Answer FAQs Pull answers from a knowledge base & support relevant navigation or form-fill

Turn off small talk Remove ad-hoc replies to small talk not found in your knowledge base

Custom message Supply your own Welcome message & process

Combine scripted responses Use predefined messages for consistent custom AI replies

MCP tools Fetch live data to pull info from outside your domain

Interested in the customization options? Learn how to create a custom Voice+ app

Head to nlx.ai, and select the Touchpoint widget to try a Voice+ experience for yourself.


Create a readymade Voice+ app

  • Select Applications in your workspace menu > Choose New application

  • Click Blank application from the available options > Choose Voice+

  • Provide a name for your application > Click Create application


Configuration

The Configuration tab allows you to provide the necessary instructions, tools, and communication method for your Voice+ app to operate.

1

AI Engine

An AI engine helps disambiguate human speech for language understanding and intent recognition and also help construct construct a package of your application whenever a new build is made. The built-in NLX model is provided for you for seamless setup.

  • Prompt: Enter a prompt explaining your Voice+ assistant's purpose, brand persona (e.g., "Talk like a Jane Austen character"), and rules for engagement with users

2

Delivery

An API channel is set up by default for easy installation on your web or mobile frontend.

  • Click the channel to configure a custom conversation timeout, whitelist domains, and choose the Voice persona of your assistant (choose from built-in Inworld AI, ElevenLabs, Hume, OpenAI, or Amazon Polly personas)

3

Functionality

If you chose to import the Voice+ quickstart template from https://platform.nlx.ai/onboarding, a knowledge base will be generated for you based on the web domain you provided.

  • Knowledge: Assign a Q&A knowledge base set up in your workspace. Unknown queries from a user will call the knowledge base to locate an answer

  • Tools (optional): Assign MCP-enabled flows for your Voice+ assistant to follow structured workflows or extend capabilities to search and retrieve information outside of your web domain

  • Click Save


Deployment

Deploying a Voice+ application type allows you to construct a build that contains a package of the prompt, functionality tools, and API channel details in the state they exist at the time the build is created. You may then deploy a successful build to make it live or roll back to a previous deployment.

1

Build

  • Click deployment status in upper right > Select Build and deploy

  • Review Validation check for critical errors or detected UX issues. Before each new build initiates, a validation check is run to provide a preview of potential errors that may cause failed builds. Detected issues are listed with descriptions and solutions

  • You may provide a Description of notable build edits as a changelog

  • Click Create build

2

Deploy

Your website provides the frontend interface (how users experience your app) via the API channel. Deploying a build pushes your updates through the API channel, effectively making your app live outside of your NLX workspace.

  • Click Deployment in upper right > Select All builds > Choose Deploy on successful build

  • Click Create deployment

Enable One-click deploy to auto-deploy every new build. From the deployment status, choose Deployment settings and turn One-click deploy on. All future builds will deploy automatically.

Once a build is made, flows added as tools can be further edited without affecting a deployed application. Only deploying a new build will impact live applications. One build can be deployed at a time and deploying any build deactivates the previous one. You can freely alternate between newer and older builds using Rollback or Deploy.

3

Install

  • Click the Configuration tab of your application > Select the API channel

  • Choose Setup instructions tab of modal > Click Open Touchpoint configurator

  • From Touchpoint site, ensure Bidirectional Voice+ is turned ON and Voice mini is toggled as the Input

  • Copy setup snippet and install to your web client


Voice+ app settings

General

Advanced

  • Set a custom timeout (in seconds) for inactivity with an end user

Danger

  • Allows you to delete your agent application. Note that a knowledge base and tools assigned will not be deleted and remain available for use with other applications in your workspace

Last updated