I made one called flyonthewall, you can upload a m4a file and it gives back transcription from openAI whisper model. Basic setup (no accounts right now) that I use to transcribe plus summarize my audio notes from my dictaphone.
Not "always on" but if you enable a recording with us, it's all searchable and even attempts to write a doc of what you were talking about to scan or answer questions about later: https://augmend.com. We do screen + audio, but audio alone does work.
