Gregory's Server
I started working on a Text-to-Speech feature in Loops.
Similar to the TikTok voice feature.
It's complicated to say the least, especially when you allow users to set the start position, nevermind breaking it up into segment layers for precision timing.
Will pause this for now and allow users to import from Camera Roll (so you can use CapCut for this), otherwise this would delay the Loops beta release for weeks.
@dansup would this be whisper on device?