An Indian AI startup just achieved SOTA with their music model.
Taan v1-preview is the world's most controllable foundation music model ever. It's 3x better with instructions than Suno.
As someone who has spent HOURS playing with Suno, rolling and re-rolling the same prompt to try and get the sound I'm after (to no avail - I usually just end up settling with whatever Suno spits out, even if it's not what I wanted), it's crazy to me that you can tell Taan "start the violin at exactly the 11th second" or "first 8s tense, pause for 2s, and then the beat drops at 10s" and it will execute your instructions to a T.
This is the way generative music models always should have been.
Oh, and it's trained on 100% licensed music + you get perpetual rights to use the music you generate commercially.
@nihilunbounded I know someone who swapped out a whole section of their paper for an AI-written version because it explained the concept better. Agree with your point on academic ethics, but the provenance of ideas is becoming hazy.
@boazbaraktcs According to Argon, the code uses a quadratic map that behaves like a linear. Classic linear codes (Reed Muller etc.) just don't work for UGC.