Saganaki22

Saganaki22 / ComfyUI-OmniVoice-TTS

Public

OmniVoice TTS nodes for ComfyUI - Zero-shot multilingual text-to-speech with voice cloning, voice design, and multi-speaker dialogue

zhu-han.github.ioomnivoice comfyui custom-nodes text-to-speech tts voice-clone
17
5
100% credibility
Found Apr 03, 2026 at 17 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Add-on tools for a visual AI workflow app that turn text into realistic speech, clone voices from audio clips, design custom voices, or create multi-person dialogues in over 600 languages.

How It Works

1
🔍 Discover OmniVoice

You find this fun voice-making add-on in your AI workflow tool's extension store.

2
✅ Install Easily

Click install and new voice tools appear in your toolbox right away.

3
Pick Your Voice Type
👤
Copy a Voice

Upload a short clip of someone talking to match their voice.

🎨
Design a Voice

Describe traits like 'young woman with soft accent'.

👥
Group Chat

Set up multiple speakers for lively conversations.

4
📝 Add Your Words

Type what you want said, add tags like [laughter] for feelings.

5
✨ Create Audio Magic

Hit the button and hear lifelike speech generate super fast.

🎉 Enjoy Real Voices

Listen to perfect talking audio in any language – just like real people!

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 17 to 17 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-OmniVoice-TTS?

This Python-based ComfyUI extension adds OmniVoice TTS nodes for zero-shot multilingual text-to-speech, supporting 600+ languages out of the box. Users get voice cloning from 3-15 seconds of reference audio, voice design via text prompts like "female, low pitch, British accent," and multi-speaker dialogue using simple [Speaker_N]: tags. It solves the pain of integrating high-quality, customizable TTS into ComfyUI workflows without custom training or language limitations.

Why is it gaining traction?

Zero-shot voice cloning and design deliver convincing results across languages without datasets, while multi-speaker nodes enable natural dialogue generation in one pass. VRAM-efficient caching, auto model downloads from Hugging Face, and SageAttention speedups on Ampere+ GPUs make it fast for iterative ComfyUI use. Install via ComfyUI Manager or git clone keeps setup painless, unlike standalone TTS tools requiring separate pipelines.

Who should use this?

ComfyUI workflow builders creating AI videos with narrated scenes, game developers prototyping multi-speaker NPC dialogue, or content creators dubbing multilingual podcasts. Ideal for anyone chaining TTS with Stable Diffusion or video nodes for voiceovers that match cloned or designed voices seamlessly.

Verdict

Grab it if you're in ComfyUI and need advanced TTS—docs are thorough, nodes are polished, and features punch above the 17 stars. At 1.0% credibility from low adoption, it's early but stable for production experiments; watch for community growth.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.