Speech recognition and natural language understanding are popular topics in the area of machine learning, yet these technologies pose some of the most challenging problems in computer science. Many Amazon Web Services (AWS) customers choose to develop conversational interfaces for their applications to provide engaging and lifelike experiences for their end users.

The AWS Cloud offers robust, flexible, and highly available services that enable machine learning on the cloud, including Amazon Lex, a fully managed service that enables developers to quickly and easily build sophisticated conversational bots (“chatbots”).

AWS customers who want to implement chatbots in other languages must develop their own backend platforms that support language analysis and abstraction, and knowledge training that is specific to their business needs. To help customers implement those chatbots, AWS offers the Serverless Bot Framework solution.


AWS offers a solution that automatically deploys, configures, and integrates with managed services such as AWS Lambda, to apply machine learning algorithms, and Amazon Polly, to turn text into lifelike speech. The diagram below presents the architecture you can deploy in minutes using the solution's implementation guide and accompanying AWS CloudFormation template.

  1. The template deploys an API Gateway endpoint where customers can send requests and Lambda functions that apply machine learning algorithms.
  2. Amazon Polly turns text into lifelike speech, an Amazon DynamoDB table stores conversation logs and interaction context, and Amazon Simple Storage Service (Amazon S3) buckets store configuration files.
  3. The solution also deploys a sample web application into an Amazon S3 bucket configured for static website hosting.
Deploy Solution
Implementation Guide

What you'll accomplish:

Deploy the Serverless Bot Framework solution using AWS CloudFormation. The AWS CloudFormation template will automatically launch and configure the components necessary to deploy, configure, and integrate with managed services to apply machine learning algorithms.

Implement chatbots in English, French, German, Italian, Portuguese, Russian, and Spanish languages.

What you'll need before starting:

An AWS account: You will need an AWS account to begin provisioning resources. Sign up for AWS.

Skill level: This solution is intended for infrastructure architects and developers who have practical experience architecting on the AWS Cloud.

Q: What languages does the Serverless Bot Framework solution support?

Currently, Amazon Lex supports US English. This solution extends the language functionality to include English, French, German, Italian, Portuguese, Russian, and Spanish languages.

Q: Can I customize the solution to fit my business needs?

Yes. The deployed Amazon S3 bucket contains a file that you can use as a reference to create your own custom knowledges that fit your business needs. For more information, see the implementation guide.

Q: Can I deploy the solution in any AWS Region?

Customers can deploy the Serverless Bot Framework solution in any AWS Region that supports Amazon Cognito.

Need more resources to get started with AWS? Visit the Getting Started Resource Center to find tutorials, projects and videos to get started with AWS.

Tell us what you think