Shulman: Generative audio AI lags text and images by one to two years
Mikey Shulman · Making Transformers Sing - with Mikey Shulman of Suno · Mar 14, 2024 · at 3:00
Mikey Shulman, co-founder of Suno, compares the maturity of audio and music generation models with text and image generative AI.
0:00 / 0:11exact quote · 11.1s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“So I think very roughly you can think audio is like one to two years behind images and text. And so you kind of have to think today like text was in 20, 22 or something like this.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Mikey Shulman
Shulman: Suno does not only train its models on music
“People are always surprised to learn that we don't only train on music.”
Shulman: Suno prohibits users from generating songs using copyrighted lyrics
“We actually don't let you do that. And it's because if you're taking someone else's lyrics, you didn't own those. You don't have the publishing rights to those. You can't remake that song.”
Shulman: AI song covers are viral novelties, not music's future
“And I think this stuff is very viral, but I actually really don't think that this is how people want to interact with music in the future.”
Suno avoids hardcoding musical rules into its generative models
“We try not to impose anything about music or audio in general into the model, and we kind of let the models learn things by themselves.”
Shulman: Understanding of music scaling laws is far behind text
“I don't think we know these things nearly as well as they're known in text. We have some notions of some of the scaling laws here, but I think yeah, we're just so, so far behind.”
Streaming throughput constraints prevent Suno from scaling to 175 billion parameters
“We care a lot about how many tokens per second we can generate because we need to stream new music as fast as you can listen to it. And so that is a big one that I think probably has us never get to a hundred seventy-five billion parameter model, if I'm being …”