Ellis - AI notes for in-person meetings
by•
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
How well does the speaker identification actually hold up in a noisy room with overlapping talk? Wondering how often I'd need to go back and manually fix who said what.
Ellis
@englyevq you can try it out for free. I purposefully designed a UI that gives you a "best match" on your voice enrollment, and a way for you to pick and label speakers by name if you need to. So the manual "fixing" should be easier
Ellis
@luki_notlowkey I'm using AssemblyAI which models are getting better and better. Do you attend conferences?
Recorded a team standup on my phone and the speaker labels were actually accurate, which I did not expect. The summary caught an action item I had completely missed during the meeting.
Ellis
@ademidqv happy to hear it helped
How well does the speaker identification hold up in a noisy room with multiple people talking over each other?
The Apple Watch recording option is clever, I tried it on a quick standup and the speaker labels were surprisingly accurate without me lugging my laptop around.
Ellis
@ayferi2xd happy to hear it
Love that you're focusing on in-person meetings
Most AI note takers are optimized for virtual calls. Being able to capture discussions with just an iPhone or Apple Watch feels really convenient. Curious, how well does Ellis handle noisier environments like conferences or busy cafés?
Ellis
@worksforme well, and getting better. Using AssemblyAI under the hood. Curious about your conference use-case. Have you tried other notetakers in the past?
how does it handle cross-talk or overlapping speakers when multiple people talk at the same time during the meeting?
Ellis
@dnde8yg you get a full transcript where you can then easily identify speakers. By cross-talk there are occasional instances where it might identify two speakers as one. But the recent AssemblyAI model is surprisingly good and getting better.
The speaker ID is surprisingly accurate even when people talk over each other, and pulling up "what did we decide about X" after the meeting feels genuinely useful.
Ellis
@fahrettinktgb thanks for your feedback
How well does the speaker identification actually hold up when people are talking over each other or moving around the room?
How well does the speaker identification hold up when a few people are talking over each other, like in a fast brainstorming session?
Ellis
@sercanpcke Give it a try! Brainstorming sessions are a perfect use-case