I bought the “kids expansion pack” yesterday. What I have been observing in using several of the voices is this: if the captured segment is longer than (approximately) 25 seconds, the sound becomes garbled after that point. I've probably captured it using 3 of the kids voices a good 20 times and this happens each time.
Examining the sound file of the applied voice (like in Melodyne) , you can clearly see that after the 25 or so seconds the wave form becomes “steps”. Almost like VoiceAI is unsure of the pitch. It's quite terrible sounding. (Note: the first part of the captured sound is fine).
What I have to do is break the sounds up into chunks that are short, this means on separate tracks in my DAW.
Note: I have the perpetual version, Win 11, 32GB.
Help.
0
Please sign in to leave a comment.
3 comments
Hi, did you get this glitch solved? Im trying to bounce the processed voices since Im using them on the chorus. I tried processing the whole track where the chorus comes in & its about 3 mins long while the processing stops after 10 seconds i guess from silence during the verses.
Hi Melmakathi,
I never did solve it. I had to break up the singing performances in short sections. As I had 3 kids across an entire song, I ended up a LOT of tracks in my song. It was a real pain.
I was happy with the end results when I did the work around…. but I am po'd that I never got a response back after I posted this original post.
I wanted to mention again that this issue was only with the child expansion pack, and not with the singers that come with VoiceAI.
I have the perpetual on Protools. This was a TERRIBLE purchase. Besides not being able to copy & paste the plugin in different spots, If i remove a processed voice & try to listen to another i cant hear a new one until i remove the plugin & start again.