Nowadays the only criteria of buying a baby cam is whether it gives you free RTSP stream access. It's the same reason people choose Obsidian over Notion.
My baby cam has built-in cry detection but it only works inside its own app. So I:
- pulled the RTSP stream from the camera
- ran YAMNet on my mini PC
- piped alerts to Telegram
Once you have the RTSP, the camera becomes a sensor. Not just sound - image + ML opens up a lot more
i compared embedding similarity between colors and emotions and normalized it to create this chart
and then when i changed the language, the results changed (eg. 赤、愛)
see: english, spanish, japanese, hindi
Spent a while picking a Dutch TTS for this. Parkiet is the best quality but heavy, and clearly trained on radio. There is even background music sometimes! mms-tts-nld from Meta is fast but robotic.
I built a pipeline that takes random posts from my old Chinese tweets, translates them to Dutch, and sends them to me as voice messages on a schedule. It's technically a language learning tool but it feels more like a time machine that speaks in Dutch.
Tbh the recommendation batch from my Eigenfeed for this week is becoming a bit boring... Probably need to give more weight to the new topics popped up in my most recent notes.
@enjojoyy I was just like you. Doing GIS and transportation was like my past life. And I’m also recently thinking about what if I just do them again with claude code. Would be fun. So your post feels so relatable. If I find any particular tools/skills/mcps, I will share!
@enjojoyy And this new open “iphone” will have a dark mode terminal on one side and a light mode browser on the other side. And it can be unfolded to have terminal and browser side by side.