Earlier quoted context omitted.
That is not actually required. You can even set empty key for that. Also Linux issue pointer: https://github.com/fastrepl/hyprnote/issues/67#issuecomment-...
I get an "EmptyToken" error if I leave keys like AXIOM_TOKEN empty. I'm sure I can remove the requirements in code, but it's just that this wasn't expected from reading the project description. Anyway, thanks for your work and good luck!
Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
181–185 of 185 posts
Re: Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
#182Re: Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
#183I'm always amazed at these relatively tiny projects that "launch" with a "customers" list that reads like they've spent 10 years doing hard outbound enterprise sales: Google, Intel, Apple, Amazon, Deloitte, IBM, Ford, Meta, Uber, Tencent, etc.
We’re firmly in a world where “cheat on everything” is an acceptable business, startups that were hacked together in a week at YC claim they have SOC2 and vibecoded GPT wrappers claim they “trained a model”. Shameless lying took over tech, and if anyone catches you lying, you double down, make a scene and a bunch of podcasts will talk about you. Free advertising! Of course, dishonesty is as old as time, but these las…
Re: Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
#184In a nutshell you ask an LLM to summarize the transcript and input some notes to help frame the results that's all ? It could be done with ChatGPT + Notepad ?
Yes it could be fully local, but to do that you need a serious computer and a way to distribute Whisper (on Windows)
FYI I tried something close, but comparing Plaud and Whisper (on Windows) Plaud wins far ahead.
Re: Launch HN: Hyprnote (YC S25) – An open-source AI meeting notetaker
#185Earlier quoted context omitted.
> finally, speaker identification is a big challenge for us too. But your home page makes it looks like you already have it. I just tried it in a 30-minute meeting with 20 people and it put the entire conversation under a single speaker, in a single paragraph.
I acknowledge that it's outdated. When we were writing the landing page, we thought we could ship the first version of speaker diarization/identification within a few days. However, due to various challenges and priority changes, we haven't been able to do so yet. We'll update the landing page soon.
1. It does not appear to work at all for me.
2. 12 days ago you mentioned that you'll update the landing page to clarify the feature.
3. As of 2025-08-11, the website still states 'Speaker Identification' as a feature: http://bit.ly/4mvN3LS