[SEO Subhead]
This Guidance helps you build a digital human that can livestream content on demand through cloud rendering, cloud livestreaming, and artificial intelligence (AI) services. You can use this Guidance to quickly build and manage the system that will control the digital human’s language, voice, and intonation based on business scenarios. Additionally, you can push the livestream video to a variety of terminals based on Amazon Interactive Video Service (Amazon IVS). The livestream is distributed through edge networks and has the ability to scale to up to 10,000 viewers.
Please note: [Disclaimer]
Architecture Diagram
[Architecture diagram description]
Step 1
The livestreaming operator uses APIs or frontend pages that encapsulate APIs to send control commands of the digital human streamer or viewers’ questions to Amazon API Gateway.
Step 2
API Gateway passes the questions to the Search & Question Answering (QA) system, powered by a large language model (LLM), and gets back suggested answers.
The QA system can be built based on Guidance for Custom Search of an Enterprise Knowledge Base on AWS. All APIs are configured with authentication. Amazon CloudWatch monitors for AWS Lambda functions and API calls.
Step 3
Lambda uses Amazon Polly to convert answers into a voice file, stores the voice file in Amazon Simple Storage Service (Amazon S3), and saves the metadata in Amazon DynamoDB.
Step 4
API Gateway passes the control commands of the digital human to a virtual reality (VR) module running a VR application hosted on Amazon Elastic Compute Cloud (Amazon EC2). We recommend using EC2 G4dn instances. Amazon EC2 Auto Scaling enhances availability.
Step 5
The VR module runs the digital human module, renders images into video streams, and pushes streams to the EC2 instances hosting the streaming module.
Step 6
Amazon Interactive Video Service (Amazon IVS) Low-Latency Streaming distributes the livestream to Amazon IVS SDK or viewers’ mobile phone and web applications. We recommend Amazon IVS real-time streaming to reduce latency.
Step 1
The livestreaming operator uses APIs or frontend pages that encapsulate APIs to send control commands of the digital human streamer or viewers’ questions to Amazon API Gateway.
Step 2
API Gateway passes the questions to the Search & Question Answering (QA) system, powered by a large language model (LLM), and gets back suggested answers.
The QA system can be built based on Guidance for Custom Search of an Enterprise Knowledge Base on AWS. All APIs are configured with authentication. Amazon CloudWatch monitors for AWS Lambda functions and API calls.
Step 3
Lambda uses Amazon Polly to convert answers into a voice file, stores the voice file in Amazon Simple Storage Service (Amazon S3), and saves the metadata in Amazon DynamoDB.
Step 4
API Gateway passes the control commands of the digital human to a virtual reality (VR) module running a VR application hosted on Amazon Elastic Compute Cloud (Amazon EC2). We recommend using EC2 G4dn instances. Amazon EC2 Auto Scaling enhances availability.
Step 5
The VR module runs the digital human module, renders images into video streams, and pushes streams to the EC2 instances hosting the streaming module.
Step 6
Amazon Interactive Video Service (Amazon IVS) Low-Latency Streaming distributes the livestream to Amazon IVS SDK or viewers’ mobile phone and web applications. We recommend Amazon IVS real-time streaming to reduce latency.
Well-Architected Pillars
The AWS Well-Architected Framework helps you understand the pros and cons of the decisions you make when building systems in the cloud. The six pillars of the Framework allow you to learn architectural best practices for designing and operating reliable, secure, efficient, cost-effective, and sustainable systems. Using the AWS Well-Architected Tool, available at no charge in the AWS Management Console, you can review your workloads against these best practices by answering a set of questions for each pillar.
The architecture diagram above is an example of a Solution created with Well-Architected best practices in mind. To be fully Well-Architected, you should follow as many Well-Architected best practices as possible.
-
Operational ExcellenceRead the Operational Excellence whitepaper
CloudWatch continually monitors the steps and performance of Lambda and API Gateway. This helps you to know when steps are blocked or have the potential to be blocked in addition to which services are causing a delay in response. Monitoring through CloudWatch helps you optimize your system over time.
-
SecurityRead the Security whitepaper
AWS Identity and Access Management (IAM) access replaces credential access between services to improve system security. With IAM, you should limit role access to the minimum permissions within the system without storing any credential information in the code and configuration. Amazon S3 blocks public access, and you can access S3 buckets with Amazon CloudFront, which protects unauthorized access from public networks.
-
ReliabilityRead the Reliability whitepaper
API Gateway, Lambda, and DynamoDB support a serverless architecture. Serverless services can automatically scale horizontally based on the actual workload. This improves reliability by reducing the chance of application failure within the livestream system.
-
Performance EfficiencyRead the Performance Efficiency whitepaper
Amazon IVS helps the system provide high-performance service to the end user. Amazon IVS achieves this through real-time streaming with latency that can be under 300 milliseconds from host to viewer, allowing you to create an engaging live video experience. Amazon IVS also provides high concurrency, allowing digital human livestream audiences of up to 10,000 viewers.
-
Cost OptimizationRead the Cost Optimization whitepaper
DynamoDB has a Time to Live (TTL) feature that can delete expired items from your DynamoDB table, reducing overall costs. For Lambda, your cost is based on the amount of time your code runs. You can also use timeout features with Lambda to minimize ephemeral storage.
-
SustainabilityRead the Sustainability whitepaper
Amazon S3 provides lifecycle configuration, a set of rules that define actions for Amazon S3 to apply to a group of objects. You can set an “expiration” feature, which configures Amazon S3 to automate the removal of retired data, reducing storage resources and effectively minimizing your workload’s environmental impact.
Implementation Resources
A detailed guide is provided to experiment and use within your AWS account. Each stage of building the Guidance, including deployment, usage, and cleanup, is examined to prepare it for deployment.
The sample code is a starting point. It is industry validated, prescriptive but not definitive, and a peek under the hood to help you begin.
Related Content
[Title]
Disclaimer
The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.
References to third-party services or organizations in this Guidance do not imply an endorsement, sponsorship, or affiliation between Amazon or AWS and the third party. Guidance from AWS is a technical starting point, and you can customize your integration with third-party services when you deploy the architecture.