Hey this is cool. I've been exploring something similar. I was stuck in some similar issues. Would love to talk to you.

I really believe that Google Meet, Zoom, etc., should be optimized for the agents so that anytime you are communicatin with each other, agents can seamlessly capture data. Right now, it's very hard to capture that kind of data from Zoom, from Google Meet, etc.

Even agents should be able to communicate and call each other.

I personally love Dictation Daddy. The support for windows and android app is amazing.

Thanks for sharing them. I am looking for modifying the text inside these via Chrome extension desktop app for my accessibility app

Are you the guy that posted on x about using iphone device as OCR?

Not sure, I may have mentioned something about iOS OCR in general (not the app, which I’ve never discussed publicly before now).

This is nice. I am building app.blinkcuts.com and trying to add b-roll functionality into it. Let's connect over mail bansal.rahul 14 @ g**l.com

This is really creative video and it got me thinking is it possible to edit such videos using AI.

The above video contains two parts one is bike crashing and the other is transition to shop advertisement.

The Editor can ask" Take this two videos and combine them together add the transition from bike crash to and entry into shop"

The challenge over here is to figure out what all extra frames needs to be removed from the two videos. Figuring out what are the two frames in the respective videos that will be merged.

The first challenge is still doable. I can analyse the frames and see which frames shows the bike crashing and which frame shows the man running.

The major challenge how will I merge them so that the transition looks smooth.

What are your thoughts on that?

Do you plan to open source it? I will love to extend it. I had similar ideas about non linear UI.

It can be more like auto suggest the one that is present in code editors.

Location: Banglore Remote: Yes, Willing To Relocate: Yes, Technologies: React, Nodejs, Python, Antd, Firebase, Docker, mongodb, postgres, chrome extension Resume https://docs.google.com/document/d/1FxSnIGi5jJB1ZIjOO2bB-ENJ... Github https://github.com/rahulbansal16 Linkedin https://www.linkedin.com/in/rahulbansalrb/ Email bansal.rahul14[@]gmail

I am former Tech co-founder of Zenlor. I can build product from scratch by talking to customers and coding them. I have worked in companies like Directi, Blooreach, Microsoft and have built and launched 11 products in the past 4-5 months and have close to 4000 users using them.

I value low ego, growth mindset, shipping fast culture.

I have been using vimium for some time now and it has become my tool for navigating around the webpages. It's so much easier to navigate around webpages. But as soon as I go out of the browser, I have to start using mouse again and it becomes very irritating. Is there vimium equivalent for Desktop? If No, How difficult will be to make something like that?