Hacker Newsnew | past | comments | ask | show | jobs | submit | robinyapockets's commentslogin

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?


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?


The issues would mostly be around stale data/ wrong titles. Even if you verify contact details periodically people can still change jobs in between.


Thanks! Good to know. Zoominfo feels expensive though.


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


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.


I have a solution to scrape job portals like LinkedIn, Indeed, and a couple more. But the jobs data's value plummet very sharply over time and extracting this data at a large scale is quite extensive. Not sure what is your though.


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


We used indeed as the pilot. Don’t try this on LI as your account will be banned.

You can also test out clay- they have a free tier that I think includes new job alerts based on LinkedIn.


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?


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: