Smart meeting assistant from AWS AI services
We all live into eternal on-line meetings. There we try to focus and take notes while trying to pay attention to the conversation. Many times you also had to quickly fact-check something that’s been said, or look up information to answer a question that’s just been asked in the call. Or maybe you need to send a quick summary over the meeting content.
Sometimes people on the call are talking in a language that’s not your first language, and you’d love to have a live translation of what people are saying to make sure you understand correctly. And after the call is over, you usually want to capture a summary for your records, or to send to the participants, with a list of all the action items, owners, and due dates.
AWS just launched a Live Meeting Assistant solution (LMA), a combination of some of their web services on speech, text recognition and LLMs for contextual queries.
The LMA sample solution captures speaker audio and metadata from your browser-based meeting app (Zoom and Chime), or audio only from any other browser-based meeting app, softphone, or audio source. It uses Amazon Transcribe for speech to text, Knowledge Bases for Amazon Bedrock for contextual queries against your company’s documents and knowledge sources, and Amazon Bedrock models for customizable transcription insights and summaries.
Everything you need is provided as open source in the GitHub repo. It’s straightforward to deploy in your AWS account.
Some of the LMA features are:
Live transcription with speaker attribution–
LMA is powered by Amazon Transcribe ASR models for speech to text. You can add to it brand names and domain-specific terminology if needed, using custom vocabulary and custom language model features in Amazon Transcribe.
Live translation–
It uses Amazon Translate to optionally show each segment of the conversation translated into your language of choice, from a selection of 75 languages.
Context-aware meeting assistant–
It uses Knowledge Bases for Amazon Bedrock to provide answers from your trusted sources, using the live transcript as context for fact-checking and follow-up questions.
On-demand summaries of the meeting–
you can generate a summary, which is useful when someone joins late and needs to get caught up. The summaries are generated from the transcript by Amazon Bedrock. LMA also provides options for identifying the current meeting topic, and for generating a list of action items with owners and due dates. You can also create your own custom prompts and corresponding options.
Automated summary and insights– When the meeting has ended, LMA automatically runs a set of large language model (LLM) prompts on Amazon Bedrock to summarize the meeting transcript and extract insights. You can customize these prompts as well.
Meeting recording–
The audio is (optionally) stored for you, so you can replay important sections on the meeting later.
Inventory list of meetings–
LMA keeps track of all your meetings in a searchable list.
Browser extension captures audio and meeting metadata from popular meeting apps– The browser extension captures meeting metadata—the meeting title and names of active speakers—and audio from you (your microphone) and others (from the meeting browser tab). LMA supports Chrome for the browser extension, and Zoom and Chime for meeting apps (Teams and WebEx coming soon). Standalone meeting apps don’t work with LMA —instead, launch your meetings in the browser.
Overview of the solution flow:
This solution can be deployed in your AWS account, we can help you build it and properly fit in your existing stack. In case you work on Azure similar solutions are available.
Reach out for more details on how to activate such powerful tools!
