Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

How do you analyze the videos with AI? Do you split the video into images and submit to AI or what? I’m curious because I’m building something similar for a client for a business use case.


We’re doing video to text transcribe on the phone then sending to LLM to turn to structured data happy to chat armin@kuky.com if you need help


so you're really only analyzing audio then, not video?




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

Search: