Description
Idk why i did this but i did Made by me me if you're using any of my models or simply don't credit me in general. Enjoy
Comments
xhepyxopila
you should take the sample audio and turn it back into a spectrogram
EmojiMELT
It seems like when you take the audio of the generated audio, then turn it into a spectrogram, It generates some REALLY weird figures/characters.
Add a comment
Samples
New
Classic
1. Singing
Male
English
2. Singing
Female
English
3. Singing (Dry)
Female
English
4. Singing (High)
Female
English
5. Singing 2
Male
English
6. Singing (Dry)
Male
English
7. Singing (Dry, High)
Male
English
Pitch
More to explore
Loading more
