Seed Audio logoSeed Audio
Seed Audio Voice Cover

Create a voice cover

Train your voice, upload a song, and render a new version sung in your voice.

1Create voice model
2Upload song
3Choose voice
4Generate cover
1

Create your voice model

Upload 30 seconds to 3 minutes of clean speech or unaccompanied singing.

2

Upload the song

Choose the MP3 or WAV you are authorized to cover. The source must be 8 minutes or shorter.

3

Choose the singing voice

Your trained voice is applied as a V5 voice persona.

My Voice

Recommended

Complete step 1 to unlock My Voice.

4

Generate your cover

Seed Audio keeps the source melody and arrangement while replacing the vocal with your voice model.

Source song
Extract melody
Replace vocal
Preserve voice
New cover
Voice model readySong readyLyrics readyPermissions confirmed

Generation usually takes a few minutes and returns two versions.