Free workflow · new

Voice Clone — speak in your voice

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

Record 5–20 seconds of clear speech and type what it should say: Chatterbox (MIT) speaks it in that voice, with controls for expressiveness and pacing. Every clip carries an inaudible watermark. Only clone a voice you have permission to use.

Model: Voice
VRAM: 12 GB+
Level: Beginner

Download workflow — free

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

You get

Voice Clone (Speak) workflow
Sample, language and delivery tips in the notes

You need

The Gmanski RunPod template (Nov 2026 image) or the voice engines installed once
A 5–20 s voice sample
12 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 — any song in your voice

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

Beginner · 16 GB+Free

Voicenew

Vocal Split — a voice sample from any song

Pull the lead vocal out of a finished song.

Beginner · 8 GB+Free