RF alarm failure

Hello, how are you? I want to do the following: I have an alarm that activates and deactivates with an RF remote, but in the morning, most of the time it doesn’t deactivate (I don’t know if sunlight affects it). I already created an automation that records a video and sends it to me, so I can watch and listen to check if the alarm went off.

Now, I want to automate this last step—I would like to send the video or audio to an AI and have it tell me if it detects a siren. However, OpenAI only allows sending images or PDFs. I tried transcribing the audio with Whisper, but I couldn’t send the audio to it.

Do you have any ideas on how I can do this? Thanks in advance!

Is there any integration that allows sending an audio file for Whisper to transcribe? Or sending audio directly to an AI? All the ones I’ve seen only work with Assist.