Suno has released version 5 of its AI music generator, featuring cleaner mixes, richer instrument separation and more complex musical arrangements. However, while the technical advances are evident, critics argue that the emotional nuance remains limited, resulting in generated vocals that sound polished yet impersonal.
What’s new in v5
According to Suno’s pricing page, v5 is available to users under current subscription plans, giving access to the most advanced model to generate music. Suno product manager Henry Phipps notes that v5 introduces more dynamic arrangements, bridges and instrumental flourishes compared to its predecessor. Vocal tracks are smoother and better integrated with instrumentation, with improved stereo field effects and clearer separation between sounds.
“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,” Phipps said after generating a song with a flute-like synth.
However, Phipps point out that the vocals often lack the subtle imperfections of human performance, such as tiny pitch wobbles or emotional cracks that give music its character. According to him, “models don’t yet understand descriptions of specific effects and recording techniques. The way the vocal is performed is most influenced by the lyrics and the general mood.”
Controls and pricing
Suno continues to support features like allowing users to upload existing audio, add vocals or instrumentals, and export songs with commercial rights when using paid plans. The v5 model is included in tiers that include monthly credit allowances, which reset each billing period.
Because song structures are more varied in v5, users may see outputs that deviate more from standard verse–chorus formats. Some creativity and prompt tuning may be needed to steer the AI toward preferred structures or moods.