There has been a huge proliferation in AI music creation tools of late, and a corresponding uptick in the number of AI artists appearing on streaming services. Well before the modern neural network revolution, though, there was an earlier tool in this same vein. [harke] tells us all about Microsoft Music Producer 1.0, a forgotten relic from the 1990s.
The software wasn’t ever marketed openly. Instead, it was a part of Microsoft Visual InterDev, a web development package from 1997. It allowed the user to select a style, a personality, and a band to play the song, along with details like key, tempo, and the “shape” of the composition. It would then go ahead and algorithmically generate the music using MIDI instruments and in-built synthesized sounds.
As [harke] demonstrates, there are a huge amounts of genres to choose from. Pick one, and you’ll most likely find it sounds nothing like the contemporary genre it’s supposed to be recreating. The more gamey genres, though, like “Adventure” or “Chase” actually sound pretty okay. The moods are hilariously specific, too — you can have a “noble” song, or a “striving” or “serious” one. [harke] also demonstrates building a full song with the “7AM Illusion” preset, exporting the MIDI, and then adding her own instruments and vocals in a DAW to fill it out. The result is what you’d expect from a composition relying on the Microsoft GS Wavetable synth.
Microsoft might not have cornered the generative music market in the 1990s, but generative AI is making huge waves in the industry today.
Personally, I could go for some Defiant Jazz. But only 5 minutes of it.
I really like the idea, maybe it just needs some better start/stop controls and static RNG seeds so it’s repeatable.
Another cool music gen program is Dennis Martensson djent (prog metal) generator … aka the djenterator.
Style is a chord progression, Band is a set of midi instruments, Personality is a set of rhythmic accents. This was very common approach in composing for video games in thr 80-90s, using a modification of a handful of functions to generate new works. Composition is decomposed to chord gen, rhythm gen, and instrument gen. Parameterization and modularity of functions can generate music quite efficiently. However variation is not the strong suit of this approach, many configurations generate very similar songs.
Sounds like 80s Madonna or Debbie Gibson.
Fancy seeing Harke here.
Not really a “hack” YouTuber. She’s very entertaining though.
I thought this was going to be about Songsmith, but that didn’t come out until the 2000s.
Someone gave me a disc back then titled “MTV music generator” I piddled around with it. Meh.
AI in the music industry is as old as Tin Pan Alley and pigeon-holing suits way back then. They did publish in digital media as well as phonograph records.