I’ve been with Capo (Mac) from the start and have found it very useful to isolate instruments (mostly bass guitar) from audio tracks (and have published many of my efforts on YouTube highlighting Capo).
However, times are a changin’. AI is now being used to isolate instruments, vocals, etc. in music. It seems Capo’s isolate mode using just frequencies and channels is becoming obsolete (but still useful for the price today) compared to AI-enhanced work. It seems that many AI apps are using Spleeter (or their APIs) spleeter.ai.
I wonder if AI-enhancements are underway for Capo?
These AI-powered source separation algorithms are very cool, and I’ve been following this area of research with a great deal of interest. However, I’m quite far away from integrating such a thing into Capo.
Right now, the dominating approach to AI separation doesn’t line up with my own set of preferences/requirements for how I imagine Capo could utilize the technology. Fortunately, this field of research is moving at such a rapid pace: I don’t think it’ll be long before my specific wishes are granted, and I can get started building this out.