I've been thinking of and briefly working on a similar project.
One idea is to analyze timing as well, and "trigger" things after certain sequences (so play 1-3-5 as say eighth notes and then get an in-rhythm arpeggio one octave higher) or detect the beat and play on the upbeat.
I haven't done any Rust, but this might give me a good reason to give a try.
Have you considered making it a plugin? (makes replay easier in my opinion, but brings other pain like relaunching the DAW between builds...)
I've got a few thoughts for features, if you're open to them:
1. Ability to specify where your "played" voice resides in the voicing: As the bass note, as an inner voice, or as the top line.
2. Options for first species, second species, third, florid, etc counterpoint for each of the generated voices. Ex: You play a single note and the upper voice plays two notes for every one of yours, etc, etc.
3. If you want to get real fancy, make the generated voices perform a canon of your played notes.
"Realtime" as in "while playing guitar" has some pretty challenging latency requirements. Even if your solution is optimal, hardware specs will play a meaningful role. I'd be really interested if you've solved for this e2e.
There was a 1970's Indonesian progressive rock band called Contrapunk that released an album called "Putri Mohon Diri" [1]
You can find the recording on YT [2]
They were really unique - blending traditional Indonesian instruments, intense guitar work and classical influences.
Nicely done! I saw you're building a cloud version so wanted to refer the excellent https://github.com/sonosaurus/sonobus which you might be able to integrate. All the best!
What a cool idea. I don't have a music setup capable of running this right now - perhaps in a couple of months - but if you were to post some sample recordings, I'd gladly listen to them.
How do you generate velocity values for the accompaniment notes?
Given that you already have a pitch tracker, it could be interesting to add key detection; just start playing, instead of telling the machine what key you're in, and it starts following along as soon as it catches on.
56 comments
FYI in this phrase: "AI is not going to kill music till people keep playing music together."
The "till" (until) kind of inverts what I think is the intended meaning.
A better replacement would be "as long as".
One idea is to analyze timing as well, and "trigger" things after certain sequences (so play 1-3-5 as say eighth notes and then get an in-rhythm arpeggio one octave higher) or detect the beat and play on the upbeat.
I haven't done any Rust, but this might give me a good reason to give a try.
Have you considered making it a plugin? (makes replay easier in my opinion, but brings other pain like relaunching the DAW between builds...)
I've got a few thoughts for features, if you're open to them:
1. Ability to specify where your "played" voice resides in the voicing: As the bass note, as an inner voice, or as the top line.
2. Options for first species, second species, third, florid, etc counterpoint for each of the generated voices. Ex: You play a single note and the upper voice plays two notes for every one of yours, etc, etc.
3. If you want to get real fancy, make the generated voices perform a canon of your played notes.
If you're interested in adding more scales, I have a wider range in my scale builder: https://xn--langy-yua.net/skala
https://steinbergmedia.github.io/vst3_doc/vstsdk/index.html
You can find the recording on YT [2] They were really unique - blending traditional Indonesian instruments, intense guitar work and classical influences.
[1] https://www.discogs.com/release/17424685-Contrapunk-Putri-Mo...
[2] https://www.youtube.com/watch?v=jb1792ZuXcY
How do you generate velocity values for the accompaniment notes?
Given that you already have a pitch tracker, it could be interesting to add key detection; just start playing, instead of telling the machine what key you're in, and it starts following along as soon as it catches on.