How to Mix AI Music Stems

A pro audio engineer explains how to get the most out of Suno

An explanatory guest article and an excellent offer of some highly recommended production services from Max Genie himself.

Unless you’ve been hiding under a rock, you’ll know that AI is now everywhere.

Music is no exception, and it’s becoming more and more common for songs to be created using one of the many AI powered music creation platforms.

Whilst these services are groundbreaking, and technically limitless in what they can do, the results can be hit and miss. And the audio quality of the output is a common weak spot.

So, what can we, as creators/prompters do about this? How can we use what we’re given and take it to the next level?

I covered, in a previous consciousness stream, the advantages of using human controlled analogue mastering to creatively craft Suno tracks without the stems. This can yield surprisingly good results.

But, with the introduction of the stemming and even studio function on Suno (and other sites), today I’m going to take it a step further - mixing the individual stems output from Suno and lifting the lid on some the processes that can elevate a track created by AI.

Suno handily gives us 10 stems and it’s generally good at identifying which instruments belong on which stem. You can reliably get a good drum track, a clear lead vocal and a solid bass track. And, to be blunt, these three things are going to be doing a lot of the heavy lifting in most mixes.

Where it can fall down in terms of quality are things like: acoustic guitars, piano tracks, string lines and, of course, backing vocals. As a result, these are usually the areas which require the most attention.

I’m going to chat through 4 ways below of how creative mixing processes can make the AI nature of the track less obvious and improve the overall sonic quality using the track kindly provided by Vox called One Last Breath.

1. The Vocal - de-verb, new processing, new reverb

2. Strings and piano room sound design

3. Guitar treatment

4. Drum track transient design

First, I highly recommend reading the whole thing there as this is little more than the introduction to the advice and instructions. Max is an absolute magician when it comes to audio production and getting the most out of an track, and I highly recommend his services. It’s worth noting that he mastered - not mixed, just mastered - the entire Soulsigma album, and managed to provide an audio quality to the AI-generated music that people found incredible at the time.

But that was before Suno permitted stem extraction and effectively did all the mixing itself. Now, with stem extraction, producers can reach an even higher level of audio quality than was hitherto possible because instead of everything being mashed together from the inception, the different elements can be separately optimized, then brought back together.

You can very clearly hear the difference Max’s mixing and mastering makes without even needing to listen to the original output. This is ONE LAST BREATH by Soulsigma, a song I wrote for a movie soundtrack.

Max has the original Suno output in his article, which will allow you to hear just how dramatic the difference is between the automixed and the professionally mixed versions. For those who already have some songs ready for the production process, he even has a Black Friday sale offer that you should definitely check out.

At this point, I wouldn’t even consider doing a public release of an AI track without having Max mix and master it. And that’s coming from a producer who a) has three Billboard Top 40 Club hits and b) beat out Prince for a Best Dance Record.

Check out Max’s various audio services here.