Enhancing Public Speaking Skills with Generative AI-Powered Virtual Assistant Using Amazon Bedrock

Introduction

Public speaking can be a daunting challenge, but it’s also an inestimable skill that enhances professional growth, academic success, and particular development. Whether delivering a business donation, giving a lecture, or engaging in social media content, the capability to communicate easily and confidently is essential.

We’ll explore how Amazon Bedrock, combined with tools like Amazon Transcribe and AWS Step Functions, can produce a scalable AI-powered Public Speaking Mentor. This virtual adjunct analyzes your speech for alphabet, language use, and common risks. It provides practicable feedback to help elevate your delivery, empowering you to become a more effective and poignant public speaker.

Amazon Bedrock is a completely managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies like AI21 Labs, Anthropic, Cohere, Meta, Mistral AI, Stability AI, and Amazon through a single API, along with a broad set of capabilities to make generative AI operations with security, sequestration, and responsible AI.

Overview of solution

• Amazon Cognito User Pool: Used for user authentication, ensuring only authorized users can access the Public Speaking Mentor AI Assistant’s web portal to upload audio and video recordings.
• Web Portal Using Streamlit: A user-friendly interface built with Streamlit allows users to upload their speech recordings. These files are then stored in an Amazon Simple Storage Service (Amazon S3) bucket for later analysis and processing.
• AWS Step Functions Workflow: A Step Functions standard workflow manages converting audio to text using Amazon Transcribe, followed by invoking Amazon Bedrock to analyze the speech, generate improvement suggestions, and offer enhanced versions.
• Amazon Simple Notification Service (SNS): Sends an email to the user, providing recommendations from Amazon Bedrock based on the speech analysis.

Image Link

Deploy the Public Speaking Mentor AI Assistant solution

1. Clone the git repository to your local machine: git repo
2. Change to the app directory in the cloned repository.

3. Create a Python virtual environment:

4. Activate your virtual environment:

5. Install the required dependencies:

6. Optionally, you can generate the AWS CloudFormation template using the AWS CDK

You might need to run a one-time AWS CDK bootstrap command using the following command:

7. Deploy the AWS CloudFormation template in your AWS account:

Create an Amazon Cognito user for authentication

1. Log in to your AWS Management Console and choose the region you desire for deployment. In the Amazon Cognito console, navigate to the side panel and select User Pools.
2. Choose the user pool created by the AWS CloudFormation template.
3. Choose Create user.

4. Enter a username and password, then choose Create User.

Subscribe to an Amazon SNS topic for email notifications

1. Log in to your AWS Management Console and select the appropriate Region for your deployment. In the Amazon SNS console, navigate to the side panel and choose Topics.
2. Choose the topic created by the CloudFormation template.
3. Choose Create subscription.

4. For Protocol, choose

5. For Endpoint, enter your email address.

6. Choose Create subscription.

Run the Streamlit application to access the web portal

1. Change the directory to webapp inside the app directory

2. Launch the Streamlit server on port 8080:

3. Take note of the Streamlit application URL for later use. Depending on how your environment is configured, you can select from one of the three URLs (Local, Network, or External) the Streamlit server provides when it’s running.
4. Ensure your local machine allows incoming traffic on port 8080 to access the Streamlit application.

Use the Public Speaking Mentor AI Assistant

1. Open the Streamlit application URL in your browser
2. Access the web portal by signing in with the Amazon Cognito username and password that you previously set up for authentication.

3. Choose Browse files to locate and choose your recording.

4. Choose Upload File to upload your file to an Amazon S3 bucket.

Once the file upload is complete, the Public Speaking Mentor AI Assistant begins processing the audio transcription and prompts engineering tasks to produce speech recommendations and rewritten results.

In the right panel of the webpage, you can view the processing steps undertaken by the Public Speaking Mentor AI Assistant to generate your speech results.

Conclusion

Individuals can improve their communication abilities in a nurturing and non-critical environment with tailored feedback and constructive suggestions. Unlock your potential to become a compelling public speaker.

Drop a query if you have any questions regarding Amazon Bedrock and we will get back to you quickly.

About CloudThat

CloudThat is a leading provider of Cloud Training and Consulting services with a global presence in India, the USA, Asia, Europe, and Africa. Specializing in AWS, Microsoft Azure, GCP, VMware, Databricks, and more, the company serves mid-market and enterprise clients, offering comprehensive expertise in Cloud Migration, Data Platforms, DevOps, IoT, AI/ML, and more.

CloudThat is the first Indian Company to win the prestigious Microsoft Partner 2024 Award and is recognized as a top-tier partner with AWS and Microsoft, including the prestigious ‘Think Big’ partner award from AWS and the Microsoft Superstars FY 2023 award in Asia & India. Having trained 650k+ professionals in 500+ cloud certifications and completed 300+ consulting projects globally, CloudThat is an official AWS Advanced Consulting Partner, Microsoft Gold Partner, AWS Training Partner, AWS Migration Partner, AWS Data and Analytics Partner, AWS DevOps Competency Partner, AWS GenAI Competency Partner, Amazon QuickSight Service Delivery Partner, Amazon EKS Service Delivery Partner,  AWS Microsoft Workload Partners, Amazon EC2 Service Delivery Partner, Amazon ECS Service Delivery Partner, AWS Glue Service Delivery Partner, Amazon Redshift Service Delivery Partner, AWS Control Tower Service Delivery Partner, AWS WAF Service Delivery Partner and many more.

To get started, go through our Consultancy page and Managed Services Package, CloudThat’s offerings.