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).
Tested it in a quick coffee chat and the speaker labels actually nailed who said what, which I did not expect. Asking "what did we decide" after felt genuinely useful instead of gimmicky.
@sgumushisa32325 happy if was useful to you. thanks for giving it a try
Used it during a quick team sync and the speaker labels were actually right on, which I was not expecting. Being able to just ask "what did we decide" after is the part that sold me.
@birol160281 happy to hear it.
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.
@ykselwil7 happy to hear it
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.
@aleynadgpp appreciate it!
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
@nazbbof happy to hear it!
the "one repository across your whole life" framing is the part that clicks for me, most notetakers box you into work context only. Apple Watch as the recording device instead of needing a phone on the table is also a nice touch for stuff like coffee meetups where pulling out a phone feels weird
@omri_ben_shoham1 thanks
no problem, good luck with the launch. curious how the Watch mic holds up in a loud cafe vs a quiet conference room, that seems like the edge case that'd make or break the "just wear it" pitch
@omri_ben_shoham1 Thanks.
Tested today in a cafe with a loud training riding by, and it was good. Haven't noticed yet, where it fails, but I'll continue to monitor it.
Give a try, if you have one. Would love to hear what you think
good to know it held up against actual street noise, that's a tougher test than most demo videos show. will give it a shot next time I'm in a meeting, curious how it does with crosstalk when two people answer at once
How well does the speaker identification hold up in a noisy room with multiple people talking over each other?