robinyapockets

Hey HN, I built Ellis, an AI notetaker for individuals, not orgs. And since my personal schedule includes meetings outside of Zoom, it was important that it works well for in-person meetings.

In fact to me, in-person conversations have always been a greater source of learning and creative ideas than virtual. On Zoom, the fixed screen and talking points tend to bring out a more transactional nature in me.

Yet building a notetaker for in-person isn't trivial. Online, each speaker has their own audio stream. In a room (or during a walk outside) everyone shares the same mic.

Models like AssemblyAI give you transcriptions with Speaker A and Speaker B, but you still have to mark yourself as the one who said X and not Y.

This is especially true if I want to get coached from my conversations. A useful use case for me as an introvert.

Here's how Ellis does this: 1) You create a voice profile of yourself (Deepgram diarization + pyannote's wespeaker model) 2) It splits the recording into speaker segments using AssemblyAI 3) It surfaces the most distinctive line from each unnamed speaker — "Moana is the best movie ever!" 4) You tap to confirm.

Remember to ask for consent! Ellis prompts you with ways to ask at the start of a recording.

Still not solved: two near-identical voices in the same room (e.g. me and my dad). Curious if anyone found a diarization approach that separates near-identical voices without per-speaker enrollment?

If you have an opinion about the tool, I'm all ears! You can try it for free.

Great idea. Where are you currently sourcing this info from?

This format is great! Thanks for the tip

Thanks. Will give a try

Ha. Guess you’re right. Have you?

Thanks! Good to know. Zoominfo feels expensive though.

We're currently experimenting, using a combination of scraping websites, social, job boards, and different data services.

Do I understand you correctly, that the company provided would have been a good lead, but the actual contact of the person, their role, etc was off?

Awesome! We'll be in touch within 48 hours.

This sounds interesting. I saw that you built https://datachroma.com/ - is this what you're referring to?

Thanks! I took a look at Apollo, and even with large discount found the price quite steep.

Nice idea with scraping job sites. Have you had any luck with any particular one?

Kinda want to avoid another CRM, and just get a smart list that I can build my own workflow around.

Have you looked for options already?

Is the problem that this kind of tool doesn't exist because hiring data is so fragmented? Some data on different ATS platforms, some on LinkedIn, but all with restricted APIs?

I'm curious about this too.

Feels like you need a specific structure in place to avoid constant context switching. Also I'm guessing it depends on the level of interaction you already have with your user base, e.g. dev tools know their customers already well, but other industries less so.

Thanks for this overview!!!

SEC filings + crowd sourcing content seems the way to go. Plus, who wouldn't want to celebrate their latest funding round :)

Curious, how much would you pay for a service where you get the same data as crunchbase, but with a delightful UI, focused on Pre Seed to A, in a vertical like "Dev Tools"?

Ooh, tell me more. What others?

You're probably right with average startup founder. But I'm thinking of first-timers, who haven't raised yet. For them, including me, it adds up quickly :)

I'm also finding missing data, and data inconsistencies. Perhaps this is a case where some data is 10x better than none.

Were you trying to expert to Excel? If so, was it mainly to sort, filter, tag, etc?

Fair point. You'd probably have to have a combination of initial data load + continuous web-scraping and crowdsourcing. Perhaps it's enough to start with a celebratory page for founders to fill out

Curious, have you used Crunchbase (premium), and if so, what's bothered you the most?

Thanks for this! We've been transparent with them from the start which helps set those expectations. Curious why you mention January?

Thanks for that framing! Very little when stated like that :)

I guess the biggest questions are (from me and other founders I've spoken to): - How does an increased volume of no-code fixes change the willingness to pay for product early on, especially when the MVP is often not more than a hack itself

- How should founders think about defensibility (even near term) when the world can look so different in just a few months.

Thoughts on that?

I'm not sure I understand exactly what your product does. Recruiting, interviewing, analysis, which one?

Thanks for the feedback! We originally thought directing users straight to app would be faster and more valuable. But you’re right, not everyone wants to download TestFlight first. We’ll create a simple landing page with highlights.

In case you’ve already used the app, which feature did you find most valuable?

Hi HN! Today we’re launching Cape - an iPhone app to answer your parenting questions based on research articles and reputable publications as an open beta (Testflight).

Here's why we built it:

We’re both parents (kids ages 1, 4, 6) and constantly inundated with parenting questions (general, situational). Typically we would search the web for answers, but found ourselves spending way too much time searching, and never really satisfied with the results (lack of trust, or personalized responses that we couldn't act upon). ChatGPT is slightly better, but the sources is still mostly unknown. What has worked was speaking with pedagogical experts in the neighborhood (when they are available).

This is our 1st attempt at providing pedagogical answers to parents while restricting the responses to scientific journals. We know we have a long way to go, but felt good enough to share for the moment with you all. Looking forward to your feedback!

New build is available. Lmk if this fixes your issue or not. I'm assuming the error is coming from your Photo permission setting. This app does not store your photos anywhere, but fetches snapshots of your photos from your Photos Library. Hence it needs to have access to those.

Thanks for the feedback! Just realized I didn't mention the required iOS 16. Let me know if that fixes the issue.

I'll take a look and deploy a new version in a couple of days.

Good point! But is this adhoc-ability something you want to support? I often think doing something adhoc never seems to benefit anybody, but happens all the time.

Does your entire team read and write to the same spreadsheet?

How satisfied are you with this tool from 1-10?

Will check it out :)

Thanks.