Oats is an AI meeting note-taking tool that is completely open, local, and free. Designed to not get in the way of your meetings, no bots, no subscription needed when running locally with on-device LLM. Available on both macOS and Windows. Enhanced transcription, multi-language support, speaker recognition, assessment, coaching, auto-tracking follow ups and more features via ariso.ai cloud backend.
We think AI meeting notes have become useful enough to be a basic utility. And basic utilities should be free, open source, and private by default.
That’s why we built Oats 🥣 -- a free, open-source AI meeting note taker for Mac & Windows.
Why Oats?
Most AI meeting tools require a bot to join your calls, send your conversations to the cloud, lock useful features behind a subscription, or use your data in ways that aren’t always obvious.
We wanted a different option.
Oats runs locally on your computer. It can record your meetings without a bot joining the call, then transcribe and summarize the conversation on-device, using local AI models.
Your recordings stay local. And because Oats is open source, you can use it, audit it, modify it, or build on top of it.
No meeting bot. No model training on your data. No data lock-in.
What you can do with Oats:
Record meetings without inviting a bot
Transcribe and summarize locally
Keep recordings on your own computer
Run with on-device LLMs
Inspect and modify the source code
Use it completely free
For those who want more, Oats can also connect to the Ariso cloud backend for enhanced transcription, multi-language support, speaker recognition, assessments, coaching, automatic follow-up tracking, and more.
Even when you use our cloud features, we will never use your meeting data to train our models, including on the free plan.
Oats is also our first step toward open-sourcing more of what we build at Ariso.
So we’d love the Product Hunt community to put it through its paces. Tell us what’s missing. Break something. Open an issue. Build something weird on top of it. Or contribute directly. 🥣
We’ll be here all day answering questions.
— The Ariso Team
Report
Is there a way to export the notes or transcript? would be nice to move them into Notion or another workspace.
@gaius_loxley Yes, they are stored locally in an Obsidian file as markdown so they are already 'exported', you can easily move them to Notion or import somewhere else
Report
Can i edit the generated notes after a meeting? would be handy for cleaning things up before sharing.
@fletcher_oliver We can get that added! We have a fairly sophisticated pipeline using github issues, so if you think of anything else feel free to add it as an issue on the github repo!
P.S. you also have a separate spot to take your own notes for a meeting, if that would suffice! It's in the app already today.
Report
What happens if I close my laptop right after a meeting?
@abod_rehman From our tests it's actually quite good, we have some novel techniques in here so it's not one-shotting the entire audio file which makes it easier for the local models to handle transcription.
@abod_rehman honestly cloud backend is a little better but the local model definitely do a fine job nowadays! You can try our cloud backend model as well. That's why give some flexibility for both
Oats
Hey Product Hunt! 👋
We think AI meeting notes have become useful enough to be a basic utility. And basic utilities should be free, open source, and private by default.
That’s why we built Oats 🥣 -- a free, open-source AI meeting note taker for Mac & Windows.
Why Oats?
Most AI meeting tools require a bot to join your calls, send your conversations to the cloud, lock useful features behind a subscription, or use your data in ways that aren’t always obvious.
We wanted a different option.
Oats runs locally on your computer. It can record your meetings without a bot joining the call, then transcribe and summarize the conversation on-device, using local AI models.
Your recordings stay local. And because Oats is open source, you can use it, audit it, modify it, or build on top of it.
No meeting bot. No model training on your data. No data lock-in.
What you can do with Oats:
Record meetings without inviting a bot
Transcribe and summarize locally
Keep recordings on your own computer
Run with on-device LLMs
Inspect and modify the source code
Use it completely free
For those who want more, Oats can also connect to the Ariso cloud backend for enhanced transcription, multi-language support, speaker recognition, assessments, coaching, automatic follow-up tracking, and more.
Even when you use our cloud features, we will never use your meeting data to train our models, including on the free plan.
Oats is also our first step toward open-sourcing more of what we build at Ariso.
So we’d love the Product Hunt community to put it through its paces. Tell us what’s missing. Break something. Open an issue. Build something weird on top of it. Or contribute directly. 🥣
We’ll be here all day answering questions.
— The Ariso Team
Is there a way to export the notes or transcript? would be nice to move them into Notion or another workspace.
Oats
@gaius_loxley Yes, they are stored locally in an Obsidian file as markdown so they are already 'exported', you can easily move them to Notion or import somewhere else
Can i edit the generated notes after a meeting? would be handy for cleaning things up before sharing.
Oats
@fletcher_oliver We can add support for that!
Oats
@fletcher_oliver We can get that added! We have a fairly sophisticated pipeline using github issues, so if you think of anything else feel free to add it as an issue on the github repo!
P.S. you also have a separate spot to take your own notes for a meeting, if that would suffice! It's in the app already today.
What happens if I close my laptop right after a meeting?
Oats
@carter_garcia I think that would pause/stop the recording/notes
Oats
@carter_garcia The audio files are queued, so you'll see an indicator saying it's ready to be processed when you re-open it.
Open source + local AI is a great combo. can users swap in their own local models?
Oats
@james_carter35 Yes we plan to add support for user's own models soon
fyi @unplug_eth0
Does Oats keep the original audio along with the transcript?
Oats
@avery_thompson2 yep, you can playback the original audio. It also supports voice profile to for speaker matching
Triforce Todos
if it is running fully local, how good is the transcription quality compared to something like otter that uses cloud?
Oats
@abod_rehman From our tests it's actually quite good, we have some novel techniques in here so it's not one-shotting the entire audio file which makes it easier for the local models to handle transcription.
Oats
@abod_rehman honestly cloud backend is a little better but the local model definitely do a fine job nowadays! You can try our cloud backend model as well. That's why give some flexibility for both