ComfyUI-DramaBox is a free extension for ComfyUI that brings expressive AI voice generation into your visual workflow. You type text, choose or clone a voice, and the system creates natural-sounding speech audio. It supports voice reference clips for voice cloning and trained voice style files for customization. The extension automatically downloads the necessary AI models on first use and integrates seamlessly with ComfyUI's node-based interface.
How It Works
You're already using ComfyUI for creative projects and hear about DramaBox for generating natural-sounding speech from text.
You add the DramaBox extension to your ComfyUI setup, and it automatically downloads the voice model when you first use it.
You enter the words you want spoken, choose a voice style, and optionally provide a short audio clip of a voice you like.
Drop in a short audio sample and the AI will match that voice's characteristics.
Connect a voice style file you trained earlier to bake that voice into the generation.
You fine-tune how long the speech should be, how closely it follows your text, and how much processing power to use.
You click generate and watch as the AI transforms your text into spoken audio, processing it step by step.
The generated voice audio appears in your workflow, ready to use in videos, podcasts, or any creative project.
Star Growth
Repurpose is a Pro feature
Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.
Unlock RepurposeSimilar repos coming soon.