Ellis is an AI notetaker for in-person meetings. Record your meeting, get a clean transcript with each speaker identified, then ask anything — what was decided, what you missed, how it went. No laptop. No extra hardware. Just your iPhone (or Apple Watch).
Replies
Best
The speaker identification was actually solid in my quick test, which I didn't expect from a phone-only setup. Wish I'd had this for the standup meetings I always forget half of.
The “AI Notes for In-Person Meetings” angle is interesting, especially for teams that still do design reviews, sales conversations, or planning sessions around a table. How does Ellis know who said what in a room? Is speaker separation part of the flow, or is it more focused on capturing clean notes and action items after the conversation?
@mia_qiao so excited that you ask :) So there's a multiple step process.
Users can record their voice during onboarding which works as a "voice enrollment."
When a meeting ends, the app displays several different cards, each with a quote and a "memorable" quote. The card that best matches the voice enrollment gets highlighted as "Best match"
The user can then assign themselves as the speaker, and add names to other attendees
When finalized the notes are updated with a new understanding of who you are in the group.
Report
The speaker identification without cloud processing feels really thoughtful, like the team actually thought through what people want during a meeting instead of just chasing the AI hype.
@uurnabb I'm trying to be as thoughtful as possible :) Thanks!
Report
The fact that it runs straight from your iPhone or Apple Watch without any extra hardware is genuinely clever, removes so much friction from actually capturing in-person conversations.
@harunartkowci Right. I understand the benefit of having an extra hardware device in that it reduces the friction of actually making a recording. But then again that requires you to purchase and upkeep a physical device.
Report
In-person notes are a different trust problem than meeting-bot notes. The useful detail is speaker correction and ownership after the recording, because the transcript becomes part memory, part operating record. Getting that boundary right matters.
How well does it handle overlapping speakers or side conversations in a noisy room, and is the transcription actually reliable enough for something like a legal or HR meeting?
Report
the fact that it runs straight off the iPhone and Apple Watch with no extra hardware is such a thoughtful move for in-person meetings.
@sedefgjlh right. So I get the purpose of hardware. It helps reduce the friction of recording, and makes it more explicit. In that sense I'm big fan of Pocket and Plaud. But that again requires you to purchase, perhaps upkeep, a physical devise
Report
The speaker identification works surprisingly well even in a noisy coffee shop, and being able to ask follow up questions about a meeting I walked out of feels like a real superpower.
Report
finally tried ellis at a coffee chat and the speaker labeling actually nailed it, even with overlapping talk. liked that i could just leave my phone on the table and forget about it
Curious how it handles crosstalk or people talking over each other in a noisy room. Does the speaker identification still hold up, or does it get messy fast?
Replies
The speaker identification was actually solid in my quick test, which I didn't expect from a phone-only setup. Wish I'd had this for the standup meetings I always forget half of.
Ellis
@ykselwil7 happy to hear it
The “AI Notes for In-Person Meetings” angle is interesting, especially for teams that still do design reviews, sales conversations, or planning sessions around a table. How does Ellis know who said what in a room? Is speaker separation part of the flow, or is it more focused on capturing clean notes and action items after the conversation?
Ellis
@mia_qiao so excited that you ask :) So there's a multiple step process.
Users can record their voice during onboarding which works as a "voice enrollment."
When a meeting ends, the app displays several different cards, each with a quote and a "memorable" quote. The card that best matches the voice enrollment gets highlighted as "Best match"
The user can then assign themselves as the speaker, and add names to other attendees
When finalized the notes are updated with a new understanding of who you are in the group.
The speaker identification without cloud processing feels really thoughtful, like the team actually thought through what people want during a meeting instead of just chasing the AI hype.
Ellis
@uurnabb I'm trying to be as thoughtful as possible :) Thanks!
The fact that it runs straight from your iPhone or Apple Watch without any extra hardware is genuinely clever, removes so much friction from actually capturing in-person conversations.
Ellis
@harunartkowci Right. I understand the benefit of having an extra hardware device in that it reduces the friction of actually making a recording. But then again that requires you to purchase and upkeep a physical device.
In-person notes are a different trust problem than meeting-bot notes. The useful detail is speaker correction and ownership after the recording, because the transcript becomes part memory, part operating record. Getting that boundary right matters.
Ellis
@krekeltronics 100% agree.
How well does it handle overlapping speakers or side conversations in a noisy room, and is the transcription actually reliable enough for something like a legal or HR meeting?
the fact that it runs straight off the iPhone and Apple Watch with no extra hardware is such a thoughtful move for in-person meetings.
Ellis
@sedefgjlh right. So I get the purpose of hardware. It helps reduce the friction of recording, and makes it more explicit. In that sense I'm big fan of Pocket and Plaud. But that again requires you to purchase, perhaps upkeep, a physical devise
The speaker identification works surprisingly well even in a noisy coffee shop, and being able to ask follow up questions about a meeting I walked out of feels like a real superpower.
finally tried ellis at a coffee chat and the speaker labeling actually nailed it, even with overlapping talk. liked that i could just leave my phone on the table and forget about it
Ellis
@nazbbof happy to hear it!
Curious how it handles crosstalk or people talking over each other in a noisy room. Does the speaker identification still hold up, or does it get messy fast?