AI Voice Changer

Input Audio

Upload the voice recording you wish to change

Your plan takes audio up to 60 seconds, video up to 30 seconds, and files up to 25 MB. You can trim longer clips before they upload.

0/1

Keep music & sound effects

Splits the voice from everything else first, changes only the voice, then puts the music and sound effects back. Turn this on for songs, or any clip with background audio.

New Voice

Select the voice you want to change the recording to

Custom Voice URL

Paste URL to a voice model. Voice models can be found using the "Search" button below

Pitch Change

Adjust pitch of AI vocals in semitones. Use positive values to increase pitch, negative to decrease.

Accent Upgrade

Control how much of the AI's accent to leave in the vocals

No accent Full accent

Filter Radius Upgrade

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

No filtering Strong filtering

RMS Mix Rate Upgrade

Control how much to use the original vocal's loudness or a fixed loudness

Input vocal's loudness Fixed loudness

Pitch detection algorithm Upgrade

'rmvpe' for clarity in vocals, 'mangio-crepe' for smoother vocals.

Crepe Hop Length Upgrade

When `f0_method` is set to `mangio-crepe`, this controls how often it checks for pitch changes in milliseconds.

Protect Upgrade

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

Leave all breath Leave none

Output Format Upgrade

wav for best quality and large file size, mp3 for decent quality and small file size.

Voice Changer

INPUT

OUTPUT