I can't get Suno to obey the style tags, it's as if they are not used at all in generating the output, or massively changed. Maybe they do the same trick Gemini used to generate the black queen of England. Or it's a trick to waste our credits faster, the only way to get something decent is to spin the dice many times.
v4.5 is a lot better at adherence with detailed descriptions!
Still not totally adherent, but if you can steer it with genre, detailed descriptions of genre, and elements of the genre it's way better than v4. Some descriptions work better than others so there's some experimentation to figure out what works for what you're trying to achieve.
You can also provide descriptions in [brackets] in the lyrics that work reasonably well in my experience.
Have been using Suno over the last few iterations and can vouch for this; steering the final product with style tags is a lot better now and I can use more natural language rather than trying to come up with what the genre specific "wordings" for certain styles of music would be. Good to know the tip about the brackets in lyrics too.
Some examples of style descriptions I've used that generated results close to what I had in mind are "romantic comedy intro music, fast and exciting, new york city" (aiming for something like the Sex and the City theme) and "mature adult romance reality tv show theme song, breakbeats, seductive, intimate, saxophones, lots of saxophones" which did indeed produce cheesy porn music.
Please make noise internally that the product desperately needs a tutorial and a prompting guide! It’s amazing if you hang out on Discord and spend a lot of time learning, but people just sitting down with it have no idea how to use it.
I'm still experimenting with what works and doesn't work. Currently for style I am trying things like:
-----
STYLE: Earth Circuit Fusion
INSTRUMENTATION:
- Deep analog synth bass with subtle distortion
- Hybrid percussion combining djembe and electronic glitches
- Polytonal synth arpeggios with unpredictable patterns
- Processed field recordings for atmospheric texture
- Circuit-bent toys creating unexpected melodic accents
VOCAL APPROACH:
- Female vocalist with rich mid-range and clear upper register
- Intimate yet confident delivery with controlled vibrato
- Layered whisper-singing technique in verses
- Full-voiced chorus delivery with slight emotional rasp
- Spoken-word elements layered under bridge melodies
- Stacked fifth harmonies creating ethereal chorus quality
PRODUCTION:
- Grainy tape saturation on organic elements
- Juxtaposition of lo-fi and hi-fi within same sections
- Strategic arrangement dropouts for dramatic impact
- Glitch transition effects between sections
---
One thing I have noticed with the new model is that it listens to direction in the lyrics more now, for example [whispered] or [bass drop], etc.
There are clear limits. I have been unsuccessful in spacial arrangement.
EDIT: I realized I didn't specify, this is when you do custom and you specify the lyrics and the style separately.
