# aws-samples/amazon-transcribe-live-meeting-assistant architecture

> Architecture diagram of the GitHub repository aws-samples/amazon-transcribe-live-meeting-assistant, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-28). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/aws-samples/amazon-transcribe-live-meeting-assistant
- Repository: https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant

## Overview

##### Project type and purpose
- This is a full-stack, serverless, event-driven AWS solution (“Live Meeting Assistant”) that captures live meeting audio (via a browser extension or direct stream), sends it to AWS services for transcription, translation, AI-driven queries and summarization, and presents real-time and post-meeting insights in a React web UI.
- Key use cases: live transcript with speaker attribution, live translation, contextual Q&A (via Amazon Q Business or Bedrock Knowledge Bases), on-demand and automated end-of-meeting summaries, meeting recordings, transcript history search.

##### File structure
- Top-level directories and modules:
- lma-ai-stack – main nested CloudFormation for core services (AppSync + GraphQL, Lambdas, Fargate task, Kinesis, DynamoDB, S3) and React UI under source/ui
- lma-websocket-transcriber-stack – WebSocket server in Fargate + supporting Lambdas
- lma-meetingassist-setup-stack – QnABot on AWS integration and custom prompts
- lma-virtual-participant-stack, lma-bedrockagent-stack, lma-bedrockkb-stack, etc. – optional feature stacks
- lma-browser-extension-stack – Chrome extension code
- Patterns: event-driven via Kinesis Data Streams, microservices style Lambdas, API layer via AppSync GraphQL, CI/CD via Makefiles and build scripts, Infrastructure as Code via CloudFormation templates.

##### README insights
- The “Processing flow overview” section outlines the end‐to‐end architecture: browser → WebSocket → Transcribe → Kinesis → Lambda “Call Event Processor” → AppSync & QnABot/Bedrock → React UI (Cognito auth, CloudFront).
- The README enumerates all AWS services, nested stacks, and data flows.

##### Main components & interactions
- Clients:
- Browser Extension (Chrome)
- React Web UI (hosted on S3 + CloudFront, authenticated via Cognito)
- Ingress:
- Secure WebSocket server (ECS Fargate behind ALB)
- GraphQL / AppSync API (WebSocket & HTTP)
- Streams & Storage:
- Amazon Transcribe (streaming)
- Amazon Kinesis Data Streams
- Amazon S3 (recordings, transcripts, build artifacts)
- DynamoDB (meetings metadata)
- Compute / Processing:
- Lambda: Call Event Processor
- Lambda: Transcript Summarization
- Lambda Hook functions (optional transcript enrichment)
- AI / Enrichment services:
- Amazon Translate
- Amazon Bedrock (LLMs & Knowledge Bases)
- Amazon Q Business / QnABot on AWS (OpenSearch)
- Amazon Lex (optional for orchestrator)
- Auxiliary services:
- Amazon Cognito (auth)
- CloudFront (static content)
- EventBridge (sync transcript KB)
- IAM roles & VPC
1. Browser Extension streams stereo audio + metadata → WebSocket server.
2. WebSocket task sends audio → Transcribe → transcription segments → Kinesis.
3. Kinesis → Call Event Processor Lambda: enrich, route to QnABot/Bedrock or custom hook.
4. Call Event Processor writes mutations to AppSync → DynamoDB & real-time updates to React UI subscriptions.
5. At call end: Summarization Lambda invokes Bedrock → summary stored in DynamoDB & S3; optionally populates transcript KB.
6. React UI queries AppSync for live segments, translations (via Translate), summaries, meeting list.
7. EventBridge periodically syncs S3 transcripts into Bedrock Knowledge Base for “Meetings Query Tool.”
c. Architectural patterns & design principles:
- Event-driven microservices: Kinesis streams, Lambdas for loose coupling and scaling.
- Serverless where possible (Lambdas, AppSync, Cognito), containerized WebSocket service for heavy audio processing.
- Nested CloudFormation stacks for modular, reusable infra.
- Least-privilege IAM roles per component.
- Extensibility via Lambda hook points and custom CloudFormation parameters.
d. Key technologies & frameworks:
- AWS CloudFormation, AWS SAM/Makefile
- AWS AppSync (GraphQL)
- AWS Lambda (Python & Node.js)
- ECS Fargate + ALB (Docker)
- React, AWS Amplify or aws-exports in UI
- Browser extension (TypeScript/JS)
- QnABot on AWS (OpenSearch + Bedrock agent)
- Transcribe, Translate, Bedrock, Q Business.

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Layers
    subgraph "Client Layer"
        direction TB
        BrowserExtension["Browser Extension"]:::client
        ReactUI["React Web UI"]:::client
    end

    subgraph "Identity & Delivery"
        direction TB
        Cognito["Amazon Cognito"]:::aux
        CloudFront["Amazon CloudFront"]:::aux
    end

    subgraph "API Layer"
        direction TB
        WebSocketServer["Secure WebSocket Server (Fargate)"]:::compute
        AppSync["AppSync GraphQL API"]:::aws
    end

    subgraph "Processing & Streaming"
        direction TB
        Transcribe["Amazon Transcribe (Streaming)"]:::ai
        Kinesis["Kinesis Data Streams"]:::data
        CallEventProcessor["Call Event Processor Lambda"]:::compute
        TranscriptSummarizer["Transcript Summarization Orchestrator Lambda"]:::compute
        FetchTranscript["Transcript Fetch Lambda"]:::compute
        MeetingControlsResolver["Meeting Controls Resolver Lambda"]:::compute
        KBQueryResolver["Knowledge Base Query Resolver Lambda"]:::compute
        TranscriptEnrichmentLayer["Lambda Hook: Transcript Enrichment Layer"]:::compute
        EventBridge["Amazon EventBridge"]:::aux
    end

    subgraph "AI & Enrichment Services"
        direction TB
        Translate["Amazon Translate"]:::ai
        Bedrock["Amazon Bedrock"]:::ai
        QnABot["Amazon Q Business / QnABot"]:::ai
        Lex["Amazon Lex (Optional)"]:::ai
    end

    subgraph "Data Layer"
        direction TB
        S3["Amazon S3"]:::data
        DynamoDB["Amazon DynamoDB"]:::data
        OpenSearchKB["OpenSearch Knowledge Base"]:::data
    end

    subgraph "Infrastructure & CI/CD"
        direction TB
        VPC["VPC & Networking"]:::aux
        MainInfra["Main AI Infra Stack"]:::aux
        WebSocketInfra["WebSocket Stack Deployment"]:::aux
        CICD["CI/CD & Build Scripts"]:::aux
    end

    %% Connections - Live Flow
    BrowserExtension -->|"audio stream"| WebSocketServer
    WebSocketServer -->|"stream audio"| Transcribe
    Transcribe -->|"transcript segments"| Kinesis
    Kinesis -->|"events"| CallEventProcessor
    CallEventProcessor -->|"GraphQL mutation"| AppSync
    AppSync -->|"updates"| ReactUI
    ReactUI -->|"GraphQL queries/subscriptions"| AppSync
    CallEventProcessor -->|"invoke hooks"| TranscriptEnrichmentLayer
    CallEventProcessor -->|"query KB"| KBQueryResolver
    KBQueryResolver --> QnABot
    KBQueryResolver --> Bedrock

    %% Post-Meeting Flow
    TranscriptSummarizer -->|"invoke Bedrock"| Bedrock
    TranscriptSummarizer -->|"store summary"| DynamoDB
    TranscriptSummarizer -->|"store summary"| S3
    EventBridge -->|"sync transcripts"| OpenSearchKB
    FetchTranscript -->|"fetch transcripts"| S3
    MeetingControlsResolver -->|"control ops"| DynamoDB

    %% Identity & Delivery connections
    ReactUI -->|uses| Cognito
    ReactUI -->|hosted on| CloudFront
    CloudFront -->|serves| ReactUI

    %% Infrastructure links
    WebSocketServer -->|runs in| WebSocketInfra
    AppSync -->|deployed via| MainInfra
    CallEventProcessor -->|deployed via| MainInfra
    TranscriptSummarizer -->|deployed via| MainInfra
    VPC -->|network for| WebSocketInfra
    VPC -->|network for| MainInfra
    CICD -->|build & deploy| MainInfra
    CICD -->|build & deploy| WebSocketInfra

    %% Click Events
    click ReactUI "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-ai-stack/source/ui"
    click BrowserExtension "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-browser-extension-stack"
    click WebSocketServer "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-websocket-transcriber-stack/source/app"
    click AppSync "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-ai-stack/source/appsync"
    click AppSync "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/blob/develop/lma-ai-stack/deployment/lma-ai-stack.yaml"
    click CallEventProcessor "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-ai-stack/source/lambda_functions/call_event_processor"
    click TranscriptSummarizer "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-ai-stack/source/lambda_functions/async_transcript_summary_orchestrator"
    click BedrockSummaryLambda "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-ai-stack/source/lambda_functions/bedrock_summary_lambda"
    click FetchTranscript "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-ai-stack/source/lambda_functions/fetch_transcript"
    click MeetingControlsResolver "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-ai-stack/source/lambda_functions/meeting_controls_resolver"
    click KBQueryResolver "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-ai-stack/source/lambda_functions/query_knowledgebase_resolver"
    click TranscriptEnrichmentLayer "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-ai-stack/source/lambda_layers/transcript_enrichment_layer"
    click QnABotSetup "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-meetingassist-setup-stack/src"
    click VirtualParticipant "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-virtual-participant-stack/backend/src"
    click BedrockKBCrawler "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-bedrockkb-stack/src"
    click BedrockAgentStack "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-bedrockagent-stack"
    click Cognito "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-cognito-stack"
    click VPC "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-vpc-stack"
    click MainInfra "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/blob/develop/lma-ai-stack/deployment/lma-ai-stack.yaml"
    click WebSocketInfra "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/blob/develop/lma-websocket-transcriber-stack/deployment/lma-websocket-transcriber.yaml"
    click CICD "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/tree/develop/lma-ai-stack/Makefile"
    click CICD "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/blob/develop/lma-ai-stack/aws-release.sh"
    click CICD "https://github.com/aws-samples/amazon-transcribe-live-meeting-assistant/blob/develop/lma-websocket-transcriber-stack/deployment/build-s3-dist.sh"

    %% Styles
    classDef client fill:#cccccc,stroke:#333,stroke-width:1px;
    classDef aws fill:#88c0d0,stroke:#333,stroke-width:1px;
    classDef compute fill:#a3be8c,stroke:#333,stroke-width:1px;
    classDef data fill:#ebcb8b,stroke:#333,stroke-width:1px;
    classDef ai fill:#b48ead,stroke:#333,stroke-width:1px;
    classDef aux fill:#d8dee9,stroke:#333,stroke-width:1px;
```
