Change the Singer

Adjust pitch of AI vocals (by a full octave)

Should the recording follow the accent of the original singer or the AI singer?

If >=3: apply median filtering median filtering to the harvested pitch results.

Which pitch-detection algorithm to use?

(For Mengio-Crepe algorithm only) How often to check for pitch changes (in milliseconds). Lower values lead to longer processing time and higher risk of (false) voice cracks, but better pitch accuracy.

Control how much of the original vocals' breath and voiceless consonants to leave in the AI vocals. Set 0.5 to disable.

Control volume of main AI vocals. Use -3 to decrease the volume by 3 decibels, or 3 to increase the volume by 3 decibels.

Control volume of backup AI vocals.

Control volume of the background music/instrumentals.

Change pitch/key of background music, backup vocals and AI vocals in semitones. Reduces sound quality slightly.

The larger the room, the longer the reverb time.

Level of AI vocals with reverb.

Level of AI vocals without reverb.

Absorption of high frequencies in the reverb.

Control how much to use the original vocal's loudness (0) or a fixed loudness (1).

WAV for best quality and large file size, MP3 for decent quality and small file size.