Suno music free download

A couple prompts (using custom mode) I’ve had success with:

1. Making it a ‘live performance.’ Really fun for covers.

Styles: “Live audience,” “crowd singing,” “live arena rock,” “live piano ballad,” “live music”

Lyrics: try starting it out with “(talking) how are you feeling out there? Sing it with me! (Crowd cheers)”

2. Add scratching to beats

Styles: “DJ scratching,” “turntablism”

Example Lyrics: “[DJ scratching] (y-y-y-yo) (li-li-listen up)”

3. Being very specific with instruments

Example Style: “Ethiopian jazz piano” will be much less generic than just “piano”

4. For hip hop beats, making it use ‘sampled’ vocals

Styles: “pitched soul sample,” “sampled track” Example Lyrics: “[high pitched soul sample, sped up] (My love) (Ooohhhhh my love)”

5. Vocal effects Styles: “vocoder,” “talk box” (limited success with these)

1. I'm trying to mix various genres that normally don't work together.

2. You can even make the vocalist scream by putting [scream] before the lyrics

3. If you part your lyrics into sections like [verse], [pre-chorus], [bridge], [chorus], [instrumental], [drop] etc. it also helps

4. You can even change the song and give it more variability by adding [Change of rythm] (almost always works for me) or if you want to end the song, just add [End of the song]. It works most of the time

5. This works only sometimes, but you can even try to add accents. I found two ways for that:

Write the name of the nationality in the prompt. Like "Russian hiphop" or "spanish pop" etc. and write your lyrics in other language than that like in English for example

Write it straight to the prompt "russian accent" etc.

6. It's weird most of the time but sometimes it's fun. You can change the genre mid song (in extend, write different genre)

7. Trying more specific or underground sub-genres or write the genre as most specific as you can. It can be pretty surprising sometimes how accurate it can be to your imagination.

We know that we can separate the lyrics with round brackets - as listed here and in the wiki - according to individual sections such as (chorus), (prechorus), (break) etc. and that these are very likely to be interpreted differently. Since I accidentally mistyped something in round brackels, I noticed that Suno sings regular words in round brackets like a chorus / choir (depending on the genre), for example, something like that gives me an extremely good result:

set me free!

set me free!

(free)

(free)

I've been using it in every song since then, depending on the genre it's sung differently in brackets, sometimes whispered, sometimes dipped in reverb, it brings in a lot of variety for me. And the best thing is that it almost always works ;) It may have been mentioned before, but I love this effect.

In order not to make a promo, I made two examples with different interpretations of this lyric prompt:

You can get multiple singers and a duet (with a little effort). Add a [Male Voice], [Male Singer] or something similar tag in the lyrics AND add verbage to the style of music (Male Singer, Male Voice, etc.)... The duet is the most difficult part but if you add duet verbage, say male and female voices, etc. to the lyrics and say [Male and Female Voices] in the lyrics you can get it with a few trys. Also using Voices with an "s" definetly helped the generation.

Example:

Edited for clarity:

Do a seperate generation for each verse/ chorus that you want to change the singer on, extend and then combine before you extend again, then just extend from the end of the verse (not the end of the song) where you liked the sound!

In my recent tests, I've starting playing around with changing the actual style prompt as well as using metatags in the lyrics prompt, and it seems to take this into account. For instance, say I'm making an Alternative song, the style prompt might read: "Alternative, Alt-Rock, Male Vocal" after a verse and chorus, I want a jazzy bridge, so in the extension where I have the "[Bridge]" metatag in the lyrics prompt, I also erase and change the style prompt to read: "Jazz, Male Vocal" or sometimes "Jazz Bridge, Male Vocal" I've had decent success with this, but like with all things, it's still a little iffy.

If you're light on tokens, it's worth noting that sometimes it will take an additional extension with the new style to give the AI time to shift gears, in my experience. So it may be better to change the style prompt and leave room before the actual bridge you want to jazzify, for instance with an [Instrumental Interlude] or something along those lines. This also applies to rhythm changes, adding instruments, or changing mood/key/mode.

As always though, all of these tips should be taken with the caveat that sometimes it just will not do what you want. It's still early in it's lifespan, and it will probably never be perfect.

1.If you want to refer to the rhythm of an existing song, you can check the BPM and Key of the song on this website and write it in as a prompt.

2. In the lyrics, you can add [Verse] (main song), [Rap] (rap), [Chorus] (chorus/climax), and [Intro] (introduction) before the lyric paragraph to better tell the AI this. How should the lyrics be sung.