I have a dumb work related chrome thing, i'd like to make it so that when a certain notification sound plays in chromium, my computer does a few things automatically for me
Does anyone know a good way to make this happen?
I imagine it'd have to be setup like:
when chrome starts playing audio && check if that audio matches soundfile.ogg && myscript.sh, but I don't know any good cli utilities that could get something like that done, and if there are any better ideas!
edit: to avoid X/Y issues i've summarized the problem in full here:
- I have a work program, this notifies me if I get a call or email, the work program then presents an accept/decline page, and does not proceed until I either accept, decline, or it times out.
- I want it to do two different things depending on if it's a call or email
- It provides no notification other than the sound and an "accept" button on the page
- I have a chrome window open that does nothing but this, and I never use chrome for anything else
- I want to automatically do various things when I receive either this call or email
- I want it to be broadly applicable rather than a script designed for the specific website giving me the notification (so not a chrome extension). This prevents me from having to update any code in the event that the backend changes dramatically, and even if the notification sound changes, i'd just record a new sound as the activation noise.
- The noise is always the same, and hasn't changed for many years, and there is a distinct noise between calls and emails
- They never overlap, they never play multiple times at the same time, and they never make any noises other than those two. The noises are distinct.
These factors cause me to want to run a script once the noise is recognized, only if the noise is playing in a particular app. I'm using pipewire/hyprland on arch.
My current plan for isolating the noise is to do the following:
pactl load-module module-combine-sink sink_name='Work' slaves='easyeffects_sink'
and then set chrome exclusively to play audio on work.
Then set a script to check the sink work for audio that matches what I want. That should be simpler than the other methods i've seen to isolate the noise.
I'll have an llm auto answer the day I fancy getting an angry call from my manager because I responded to him asking me to give him access to something with
"I'm sorry, but as an AI language model I am unable to do that"
"As an AI model, I cannot in good conscience give you access, explain clearly why you think you need access to this system and I will forward your message to a more competent authority"
It's got the right level of sass at least