[r618]

i've been occasionally trying to get some usable ambience tracks from these various models, but none of them seem to be able to produce looping tracks

based on results so far it also looks like more flexible approach to ai generation would be to generate set of stems/samples based on user description and let them to actually compose instead of producing complete audio (maybe this is already happening somewhere)

- in either case, properly looped tracks will be most likely necessary to be produced by these models at some point

[bambinella]

Creating looping sections with Sunauto is generally not very difficult as the model is overly consistent when extending, so all you have to do is extend without changing the prompt and you should get a loop point.

If you have lyrics in your conditioning then you usually can use a [Chorus] section as your loop point as most music AI models render chorus section in away that affords crossfades. THAT ASSUMES that you keep the chorus sections with a gap less than about 60 seconds with 30 seconds exention as it can only see 90 seconds of the music track (or something in that range)

[r618]

- no lyrics and no chorus- i mentioned ambience track - these are instrumental, often minimalistic they don't attract attention...

> Creating looping sections with Sunauto is generally not very difficult as the model is overly consistent when extending

the point is not consistent extension, but consistent extension (if any) plus starting audio

have you actually did this and got usable looped track ?

[zaptrem]

You can create a looped track by combining the song generation and transition generation examples from our API example repo!

[r618]

would you be so kind and

- link to both example

- briefly outline process of combining them for this usecase

- since this is API usage i suppose it's most likely not viable to obtain (reasonably) looped audio via user prompting (i.e. what's currently available in browser) - would that be correct ?