HM-RunningHub

HM-RunningHub / ComfyUI_RH_VoxCPM

Public

This is a ComfyUI plug-in for VoxCPM

20
1
100% credibility
Found Apr 12, 2026 at 20 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Custom nodes for ComfyUI enabling advanced text-to-speech with voice design from descriptions, precise voice cloning from audio, LoRA customization, and multi-speaker dialogues using VoxCPM technology.

How It Works

1
🔍 Discover Voice Magic

You stumble upon ComfyUI_RH_VoxCPM, a delightful tool that brings custom voices and speech to life right inside your ComfyUI playground.

2
📦 Add to Your Workspace

Easily bring the voice tools into ComfyUI using the built-in manager or a quick setup so everything feels seamless.

3
⬇️ Gather Voice Essentials

Pick up free voice building blocks from trusted online spots to power up your creations.

4
⚙️ Ready Your Voice Engine

Choose and load a voice base, making it all set for designing or copying voices.

5
✨ Shape Your Dream Voice

Describe a unique voice like 'cheerful elderly man' or upload a short audio clip to perfectly mimic its style and emotion.

6
📝 Type and Generate

Enter the words you want spoken, adjust a few simple sliders, and press go to create realistic speech.

🎉 Hear It Come Alive

Play back the stunning audio of your custom voice, perfect for videos, stories, or fun projects.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 20 to 20 stars Sign Up Free
Repurpose This Repo

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 Repurpose
AI-Generated Review

What is ComfyUI_RH_VoxCPM?

This Python plug-in integrates VoxCPM TTS models into ComfyUI workflows, enabling tokenizer-free speech generation with context-aware cloning and voice design. Describe voices via text prompts like "warm young woman" for new timbres, or upload reference audio for controllable style tweaks or ultimate nuance-for-nuance replication. It streamlines TTS into ComfyUI's node graphs, skipping clunky standalone tools for seamless audio pipelines.

Why is it gaining traction?

VoxCPM's edge in true-to-life cloning and multi-speaker support (up to 5 voices in tagged scripts) beats basic TTS nodes, with auto-ASR, denoising, and LoRA loading as bonuses. Installs easily via ComfyUI Manager or git clone from the ComfyUI GitHub repository, with workflows ready for download. Developers dig the AMD, Mac, and portable ComfyUI GitHub compatibility, plus HF/ModelScope model pulls.

Who should use this?

ComfyUI builders generating voiceovers for AI videos or podcasts, especially multi-speaker dialogues. Indie game devs needing dynamic NPC speech with custom clones. Krita AI SD or ComfyUI plug-in tinkerers extending workflows with VoxCPM voices on varied setups like ComfyUI GitHub portable or Mac installs.

Verdict

Promising for VoxCPM fans in ComfyUI, with strong docs and examples offsetting 20 stars and 1.0% credibility—still maturing, so prototype first. Worth the ComfyUI GitHub install if advanced TTS fits your stack.

(178 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.