GMANSKI●Try it free

Workflows / Voice

Free workflow · new

Voice Clone — any song in your voice

Same song, same backing track, your voice singing it.

The lead vocal is split from the music, re-sung in the voice of a short sample (SoulX-Singer, Apache 2.0) and mixed back. Melody and timing stay; the octave follows the new voice. Saves the remixed song and the dry vocal. Only clone a voice you have permission to use.

Model
Voice
VRAM
16 GB+
Level
Beginner
Download workflow — free

Drag the .json onto ComfyUI. Runs best on the Gmanski RunPod template.

You get

  • Voice Clone (Sing) workflow
  • Song + dry vocal outputs

You need

  • The Gmanski RunPod template (Nov 2026 image) or the voice engines installed once
  • A song and a 5–20 s voice sample
  • 16 GB VRAM

Pairs well with.

ACE-Stepnew

Song from an idea — ACE-Step

A second song engine. Apache 2.0, 8 steps.

Beginner · 16 GB+Free
Voicenew

Voice Clone — speak in your voice

Ten seconds of your voice. Any text, 23 languages.

Beginner · 12 GB+Free
Voicenew

Vocal Split — a voice sample from any song

Pull the lead vocal out of a finished song.

Beginner · 8 GB+Free