Chatterbox TTS Voice Cloning ComfyUI Workflow & One Click Installer
$3.00
✓ In Stock⭐ Get all 75+ installers for $10/month
Local Lab Pro gives you instant access to all 75+ installers and workflows we've ever made — plus every new release the moment it drops. No buying individually. One membership, everything included.
View Local Lab Pro membership →Secure checkout via Wix — or get all 75+ with Pro
// About this product
Run the state-of-the-art Chatterbox TTS directly in ComfyUI! Install locally with one click and upload the custom workflow to get started.
Chatterbox is a cutting-edge open-source text-to-speech (TTS) solution, delivering performance and compatibility on par with ElevenLabs TTS. Join for exclusive access to a one-click installer that downloads and sets up everything you need—plus, enjoy an enhanced UI version that unlocks even more model compatibility options.
Requirements
-
Nvidia GPU
-
FFmpeg
-
Windows machine
-
15 GB of storage space
Installer Features
-
Automatic Dependency Setup: Installs Git and 7-Zip if missing—no manual steps required.
-
ComfyUI Pre-Configured: Downloads and extracts the latest portable ComfyUI for Windows (NVIDIA).
-
Custom Nodes Included: Installs ComfyUI-Manager, ComfyUI_Fill-ChatterBox, ComfyUI-KJNodes, rgthree-comfy, ComfyUI-VideoHelperSuite, ComfyUI-DeepExtract, and comfy_mtb nodes for this workflow.
-
All Models Downloaded: Automatically fetches and stores the Chatterbox TTS model in your Windows cache folder.
-
No Python Hassles: Uses embedded Python—no separate installation or configuration needed.
-
Truly One Click: Just run the installer and everything sets up automatically, even on a fresh Windows system.
Installation Instructions
-
Download the batch file below and place it in a dedicated folder.
-
Install FFmpeg if not already installed (see ffmpeg.org or gyan.dev/ffmpeg/builds) and reboot if necessary.
-
Run the batch file to start installation.
-
Launch the project by running start.bat.
Usage Notes
-
The workflow includes three voice features: text-to-speech, audio-to-audio voice change, and audio background sound removal with voice change.
-
For best results, keep audio inputs to 30–45 seconds max.
-
If the preview audio node doesn’t display audio, try switching to a different workflow tab in ComfyUI and then switch back; the audio should appear.
-
Disable workflow features you’re not using to avoid errors.
Need Help or Have Questions?
Original GitHub Repository:
https://github.com/filliptm/ComfyUI_Fill-ChatterBox
- Join my Discord community for support:
- Discord - https://discord.gg/5hmB4N4JFc