"During a demo, Henry Phipps, a Suno product manager, pointed to a song we had the model generate that included a flute-like synth with what sounded like a ping-pong delay effect on it: "I've never heard that before in previous models... what that says to me is that the model understands that this is an isolated sound that's being affected and needs to be reproduced faithfully in different parts of the stereo field.""
"There are some across-the-board upgrades in audio quality that are undeniable, like fewer artifacts and clearer separation between instruments. Some tracks produced using v4.5+ can smush all the melodic parts together in a way where the lines between guitar, bass, and synth are muddy at best. But with v5, the mixes are much cleaner."
"There are no edges to any of the Suno vocals. Everything is bathed in reverb, layered with harmonies, and perfectly on pitch. Even if you explicitly tell it not to do these things, the model just ignores you."
Suno v5 brings measurable audio-quality improvements, including fewer artifacts and clearer separation between instruments, resulting in cleaner mixes than earlier versions. The model can identify isolated sounds and reproduce stereo-like effects, suggesting stronger internal representation of timbre and spatial placement. Vocal outputs remain overly refined, consistently drenched in reverb, layered harmonies, and flawless pitch, producing an uncanny, inhuman quality. The model can ignore explicit instructions to avoid those vocal traits. Claims of improved genre understanding appear inconsistent across prompts. Ongoing legal pressure from major record labels continues to affect Suno's operations.
Read at The Verge
Unable to calculate read time
Collection
[
|
...
]