AI Central is fortunate to be among those granted early access to the very exciting new beta of Suno Studio, which among other new feature, offers the ability to edit and generate sections of new music on a stem-by-stem basis. Suno has provided an introductory video for Studio, which is available on YouTube or can be watched here.
We will be posting a full review of Suno Studio once we’ve had the chance to actually get our heads and hands around the new features. In the meantime, we have the following observations:
The video skipped a necessary step, as it is first necessary to Extract Stems before clicking on Insert All.
It would be useful to inform the users that this Extract Stems process takes a few minutes. The video is, understandably enough, a little misleading in this regard, since who wants to watch a demo of someone sitting around waiting for the process to play out.
This first version of Suno Studio does not APPEAR to make it easy to replace a section of a vocal stem. However, since the first video focused solely on changes to the instrumental tracks, we may be missing a trick or two. There should still be a way to modify a small section of vocals, but it may be more complicated than we’d originally envisioned.
How about podcasting? Is there an API for say Grok or Claude to feed this text to get Howard Cosell giving the weather?
If it can generate DTMF tones on the fly, there might be all kinds of black hat shenanigans
Looks amazing. I signed up for the wait list as well. Can't wait to try it out!