Photo by

Meeting Minutes

Improve Meeting Efficiency with An AI-Driven Executive Summary

Nov 7, 2022
3 min read

During work meetings, it is important to log down all of the important data- who attended, what was discussed, what was decided, etc. This information is critical to keeping a company organized and being able to address details once the meeting has ended. When in a meeting, the one focus should be the discussion, not making sure all the information is being recorded. This critical error has the potential to lose vital information or even abandon the discussion itself.

Luckily, OneAI has the ability to help us stay focused throughout these meetings by recording all of the important information, without us having to worry about it. Utilizing the OneAI system as an extra step in your transcriptions or as an extension for your consumers is essential to maintaining an organized system.

Meeting Minutes are transcripts that are recorded during meetings. These transcripts contain critical information that essentially surround the important aspects of these meetings. This information can include key topics discussed, decisions that were made, a list of attendees, and much more.


Get the perfect Meeting Minutes in the Studio.

First, let’s jump to OneAI’s Language Studio

As you can see in the picture below, this is how the site looks like. The tool input is where you will be entering the content, alongside it is the pipeline box- this is where the magic happens.

Underneath the pipeline box, you can see the Language Skills, which are different ways we can apply the AI to the content provided. There are different skills we can apply, such as ‘Summarize,’ ‘Proofread,’ ‘Names’- today we will be clicking on ‘Transcribe Audio.’

The purpose of this Language Skill is to create a transcript for the audio provided.

Meeting Minutes AI

This meeting clip from Youtube will serve as our example for today.  

Let’s head over to this website, this will let us download the video as an audio. After inserting the link and downloading it as an audio we can head over to OneAI’s Language Studio and upload our audio file. 

There are a couple things we will be looking for in the video- meeting minutes, participants, action items, dates and times, and feedback analysis- we’ll go over everything step-by-step. 

First, to obtain meeting minutes, we can go ahead and double-click the box that says “Transcribe Audio” (however, it should be applied automatically). We recommend adding the skill “Proofread”- to prevent any grammatical errors and reduce filler words- so go ahead and double-click that box. 

Next double click the box titled “Names”- this will allow you recognize the participants- any time names, places, or products were mentioned- the software will recognize it through this skill. 

Now let’s continue to focus on action items by double-clicking the box titled “Action-items” in the section ‘Insights’, go ahead and also double-click the box “Numbers & Time '' - this will recognize any important dates and times

Next, to help us recognize any important feedback analysis- the “Emotions” skill will come in handy. This will highlight any positive or negative reactions in the dialogue.

Finally, let’s opt for a high-quality summary to read the main objective of the meeting- double-click the box that says ‘Summarize.’

Now click the box on the top right corner titled ‘Run Pipeline’ and let’s see the results: 

Meeting minutes Language Studio

And just like that, we successfully got everything we needed. Now it’s time to copy the code and proceed to the code editor. 

Step 2: Run “pip install oneai” for Python SDK or “npm install oneai” for Node.js SDK to get the library. Make sure to import all the required packages:

```import oneai

import base64

oneai.api_key = "[YOUR ONEAI API KEY]"


In our example, we used Python SDK code. Here is what we got when we run all the skills together: transcribe, proofread, emotions, name, numbers & time, and summary:


with open("AudioFile.mp3", "rb") as f:


    pipeline = oneai.Pipeline(

      steps = [









    transcription =


Here are the outputs:







[00:00:01.370] speaker 1:If it's like my family, I AMdefinitely have no subject.[00:00:07.070] speaker 2:Hey, Daniel here.[00:00:09.290] speaker 2:Hello.[00:00:09.650] speaker 2:Welcome.[00:00:10.250] speaker 2:Welcome back Eric.[00:00:11.630] speaker 3:Thanks so much.[00:00:12.350] speaker 3:Yeah, it's great to be here.[00:00:14.090] speaker 2:Hi, Virginia.[00:00:17.510] speaker 2:Hello.[00:00:19.370] speaker 2:All right, let's kick off.[00:00:23.750] speaker 2:I wanted to start out with some reminders.[00:00:27.830] speaker 2:First, we have a book club coming up on inspired in four weeks on August 7th.[00:00:33.290] speaker 2:I just reread it myself.[00:00:35.090] speaker 2:It's a good read.[00:00:36.530] speaker 2:It's highly aligned with how I think about product management and does a good job of explaining why some of these things are important.[00:00:46.310] speaker 2:That I have also believed to be important, so it's nice to have another voice explaining all of that.[00:00:52.910] speaker 2:So please do read that.[00:00:54.290] speaker 2:I think I'm going to update the new hire onboarding Doc and ask all of new hires to read this as well so that


everybody in the team is on the same page with respect to this book.[00:01:10.610] speaker 2:Let's see.[00:01:12.170] speaker 2:Reminder B remember there's this interview spreadsheet, CS and sales have populated that with a number of customer contacts for meetings.[00:01:23.570] speaker 2:Please do follow up on that.








There is a book club coming up on August 7th. There is an interview spreadsheet, CS and sales have populated that with a number of customer contacts for meetings. The company has a goal of at least three customer interviews per p.m. It has a third group in the managed area in Gable lead. It's been a little while since the handbook was written. There's a diff highlights what is new content, and there's one section that is great.


Names, Organizations and Locations mentioned in the meeting:


print([[,x.value] for x in transcription.transcription.proofread.names])




[['PERSON', 'Daniel'], ['PERSON', 'Eric'], ['GEO', 'Virginia'], ['PERSON', 'Doctor (title)'], ['PERSON', 'Fabian'], ['PERSON', 'Jessica Theresa'], ['PERSON', 'Jessica'], ['PERSON', 'Fabian Forte'], ['PERSON', 'Carina'], ['PERSON', 'Scott'], ['PRODUCT', 'Gmail'], ['PERSON', 'Paul'], ['PERSON', 'Josh'], ['PERSON', 'Kenny'], ['PERSON', 'Josh'], ['PERSON', 'Gabe weaver'], ['PERSON', 'Gabe'], ['PERSON', 'Gable'], ['PERSON', 'Alan Dershowitz'], ['PERSON', 'Christy'], ['PERSON', 'David Nakamoto'], ['PERSON', 'Chris Christie'], ['PERSON', 'Sid'], ['PERSON', 'Cerro Donald'], ['PERSON', 'Josh'], ['PERSON', 'Nicole'], ['PERSON', 'Scott'], ['PERSON', 'Scott'], ['ORG', 'GitLab'], ['PERSON', 'Lucas'], ['PERSON', 'Josh'], ['ORG', 'Kenny'], ['PERSON', 'Eric'], ['PERSON', 'Jason'], ['ORG', 'YouTube'], ['ORG', 'YouTube'], ['ORG', 'YouTube'], ['PRODUCT', 'Zoom'], ['ORG', 'YouTube'], ['ORG', 'YouTube'], ['ART', 'release radar'], ['PERSON', 'Kenny'], ['PERSON', 'James, son of Zebedee'], ['PERSON', 'Mark'], ['PERSON', 'Fabian'], ['GROUPS', 'Europe'], ['PERSON', 'James VI and I'], ['ORG', 'Google'], ['PERSON', 'Fabian Forte'], ['PERSON', 'GV'], ['PERSON', 'James'], ['ORG', 'Google'], ['PERSON', 'Christopher'], ['ORG', 'Redis'], ['PERSON', 'Christopher'], ['PERSON', 'Macintosh'], ['ORG', 'Amazon (company)'], ['ORG', 'Amazon (company)'], ['PERSON', 'Christopher'], ['PERSON', 'Kenny'], ['ORG', 'GitLab'], ['ORG', 'Geo'], ['PERSON', 'Marin'], ['PERSON', 'Chris'], ['PERSON', 'James, son of Zebedee'], ['PERSON', 'Scott'], ['PERSON', 'Marin County, California'], ['PERSON', 'Marin'], ['PERSON', 'Marin'], ['PRODUCT', 'GitLab'], ['PERSON', 'Christopher'], ['PERSON', 'Christopher'], ['PERSON', 'Don (given name)'], ['PERSON', 'Josh'], ['PERSON', 'Karina'], ['PERSON', 'Scott'], ['PERSON', 'Karina'], ['PERSON', 'Christopher'], ['PERSON', 'Ericsson'], ['PERSON', 'Christie'], ['PERSON', 'Karina'], ['PERSON', 'Josh'], ['PERSON', 'Tampere'], ['PERSON', 'Josh']]




print([[] for x in transcription.transcription.proofread.emotions])




[['happiness'], ['happiness'], ['happiness'], ['happiness'], ['happiness'], ['happiness'], ['happiness'], ['happiness'], ['happiness'], ['happiness'], ['happiness'], ['happiness'], ['happiness'], ['happiness'], ['happiness'], ['sadness'], ['anger'], ['sadness'], ['happiness'], ['happiness'], ['happiness'], ['happiness'], ['happiness']]


Numbers and dates:


print([[,x.value] for x in transcription.transcription.proofread.numbers])




[['ORDINAL', '1'], ['DURATION', '4 Weeks'], ['DATE', '2023-08-07'],

['ORDINAL', '3'], ['DURATION', '1 Month'], ['DATE', '2022-11-03'],

['DURATION', '1 Minute'], ['NUMBER', '5'], ['NUMBER', '1'], ['NUMBER', '3'],

['DURATION', '3 Weeks'], ['DATE', '2022-11-02'], ['NUMBER', '3'],

['NUMBER', '1'], ['DATE', '2022-10-24 00:00'], ['NUMBER', '1'], ['NUMBER',

'2'], ['ORDINAL', '4'], ['ORDINAL', '3'], ['ORDINAL', '3'], ['NUMBER', '1'],

['NUMBER', '1'], ['NUMBER', '10'], ['ORDINAL', '1'], ['NUMBER', '10'],

['NUMBER', '1'], ['ORDINAL', '1'], ['NUMBER', '1'], ['ORDINAL', '1'], ['ORDINAL', '1'],

['NUMBER', '2'], ['NUMBER', '1'], ['DATE', '2022-11-02'], ['DATE', '2022-10-31 00:00'],

['NUMBER', '2'], ['NUMBER', '3'], ['NUMBER', '14'], ['DURATION', '1 Month'],

['NUMBER', '1,000'], ['NUMBER', '1'], ['NUMBER', '1'], ['DURATION', '20 Minutes'], ['NUMBER', '1'],

['NUMBER', '3'], ['NUMBER', '2'], ['NUMBER', '3'], ['NUMBER', '500,000'],

['NUMBER', '2'],

['DURATION', '3 Minutes'], ['TIME', '14:00'], ['NUMBER', '2'], ['NUMBER', '2'],

['DURATION', '1 Minute'], ['DATE', '2022-12'], ['NUMBER', '25'],

['DURATION', '2 Minutes'], ['DATE', '2022-11-02'], ['DURATION', '1 Minute'],

['DATE', '2022-11-02'], ['NUMBER', '1'], ['DURATION', '30 Minutes'],

['MONEY', '1'], ['DATE', '2022-11-02'], ['NUMBER', '1'], ['NUMBER', '50'],

['DURATION', '1 Day'], ['NUMBER', '1'], ['NUMBER', '3'], ['NUMBER', '1'],

['NUMBER', '30'], ['DATE', '2022-12'], ['NUMBER', '1'], ['NUMBER', '0.5'],

['DURATION', '1 Hour'], ['NUMBER', '4'], ['NUMBER', '1'], ['DATE', '2022-12-03'],

['PERCENT', '50'], ['NUMBER', '1'], ['NUMBER', '2'], ['NUMBER', '1'],

['NUMBER', '1'], ['NUMBER', '100'], ['NUMBER', '1'], ['NUMBER', '1'],

['NUMBER', '1'], ['DURATION', '1 Week'], ['NUMBER', '1'], ['NUMBER', '5'],

['DURATION', '1 Month'], ['NUMBER', '1'], ['NUMBER', '2'], ['NUMBER', '1'],

['NUMBER', '1'], ['NUMBER', '1'], ['DATE', '2022-10-24 00:00'], ['NUMBER', '20'],

['NUMBER', '30'], ['NUMBER', '50'], ['NUMBER', '2'], ['DATE', '2022-11-02'],

['ORDINAL', '1'],

['DATE', '2022-11-02'], ['DATE', '2022-11-01'], ['NUMBER', '4,000,000'], ['DATE', '2023-05'], ['ORDINAL', '1'], ['NUMBER', '1,000,000,000'], ['NUMBER', '20,000'], ['ORDINAL', '2'], ['ORDINAL', '1'], ['DURATION', '1 Month'], ['ORDINAL', '1'], ['ORDINAL', '1'], ['DATE', '2022-12-01'], ['NUMBER', '1'], ['NUMBER', '1'], ['NUMBER', '1'], ['NUMBER', '2'], ['ORDINAL', '1'], ['NUMBER', '1,000,000'], ['NUMBER', '1'], ['NUMBER', '6'], ['DATE', '2022-11-07'], ['NUMBER', '10'], ['DATE', '2022-11-01'], ['NUMBER', '1'], ['NUMBER', '7'], ['NUMBER', '1'], ['ORDINAL', '2'], ['NUMBER', '1'], ['DATE', '2022-11-20'], ['DURATION', '30 Days'], ['NUMBER', '2'], ['DATE', '2023-05'], ['NUMBER', '1'], ['DURATION', '5 Minutes'], ['DATE', '2022-11-08']]



When we go to our work meetings, the one thing on our mind should be “getting things done.” Essential information can go unrecorded or even recognized when we have to multi-task. Using today’s tutorial and OneAI’s system- your #1 focus can be on the meeting, letting you feel comfortable knowing all the information will be available for you with the use of a few buttons.

Luckily for us, OneAI has different Skills that are curated to help you out with any project. Feel free to check out our API and Language Studio to find the perfect Language Skill for your task.

Streamline Meetings with OneAI


Solely based on your most up-to-date content – websites, PDFs, or internal systems – with built-in fact-checking for enhanced trust.

Read Next