author here, yes you can copy and redistribute binary

what do you find shady about FOMO?

hey sorry about this, we improved voice activity detection since then, also you can use deepgram if you want higher quality

Good to hear you improved it. I just need it to be as good as standalone whisper-large. I certainly don't want to send all my conversations to a third party.

to easily take advantage of all these recordings, we're making it easy to extend them and, as the LLM context grows every day and video/image/audio LLMs arrive, we'll be able to ingest a week or a lifetime of 24/7 human recordings

I was liking what I was seeing, and I appreciate you making your business model very clear.

But then I saw that users can get it free by posting "about screenpipe 10 times on social media".

If you want ads, pay for proper ads! Don’t pay people to turn user content into sneaky ads.

I understand why people hate regular ads, but IMO affiliate promotion (when done without disclosure) and stuff like what you are doing is much worse.

That's cool! I use Tesseract, Whisper, and now Apple & Windows native OCR here:

https://github.com/louis030195/screen-pipe

And we also add LLM layers to fix errors

cool will look into it!

I just use python temporarily for the OCR. But the plan is to implement Apple Vision & other OS native impl