Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 

Repository files navigation

OmniVoice-Portable

OmniVoice Portable One-Click Launcher: High-Quality Text-to-Speech & Voice Cloning Software

image

If you’ve been keeping up with the latest in AI audio, you already know about OmniVoice (by k2-fsa). It is an absolute game-changer for high-quality voice cloning and text-to-speech. However, getting it to run locally can be a massive headache—dealing with Python environments, PyTorch versions, CUDA dependencies, and GitHub clones can take hours.

I wanted everyone to be able to experience this incredible AI without the technical barriers. So, I have created a Windows Portable 1-Click Startup Package for OmniVoice!

No installations, no complicated code, and no troubleshooting errors. Just download, extract, and use.

📦 What Makes This Package Special?

Zero Installation Required:* Forget about installing Python, Git, or complex dependencies. Everything you need is pre-packaged.

Truly Portable:* You can run it straight from an external SSD or a USB drive. It leaves no messy files on your system.

One-Click Start:* Simply double-click the startup file, and the intuitive Web UI will automatically open in your browser.

Private:* Once downloaded, everything runs locally on your own GPU. Your data and audio never leave your PC.

🔥 What Can OmniVoice Do? (Powered by k2-fsa)

🎙️ Zero-Shot Voice Cloning:* Clone almost any voice with state-of-the-art accuracy using just a short reference audio clip.

🌍 Massive Multilingual Support:* Supports over 600+ languages natively—the broadest coverage of any open-source TTS today.

🎭 Lifelike Emotional Control:* Add non-verbal cues directly into the text (e.g., [laughter], [sigh], [sniff], [surprise-wa]) to make the voice sound hyper-realistic.

🛠️ Voice Design: Don't have a reference audio? You can generate a brand-new voice simply by typing its attributes (e.g., "young female, British accent, high pitch"*).

⚡ Blazing Fast:* Powered by a highly optimized diffusion language model architecture, it generates audio significantly faster than real-time.

🛠️ How to Use:

  1. Download the provided .zip file.

  2. Extract it to a folder on your PC (preferably on an SSD with plenty of space).

  3. Double-click the Launch the software.exe file.

  4. Wait a few moments for the console to load—it will automatically open the interface in your default web browser.

  5. Upload an audio sample, type your text, and start generating!

Note: The first time you launch the software, it will automatically download the model files from HuggingFace.

Video Tutorials:https://www.youtube.com/watch?v=KjEe69y_75Q

💻 System Requirements:

OS:* Windows 10 / Windows 11 (64-bit)

GPU:* Dedicated NVIDIA GPU (Recommended: 6GB VRAM or higher for smooth generation)

Storage:* Make sure you have enough free space for the extracted files and models.

Path Requirements:* Ensure that the software installation path, the source file names, and the output paths do not contain non-English characters or spaces.

Thank you so much for your incredible support! ❤️

Your pledges make it possible for me to dedicate time to building these easy-to-use, one-click tools for the community. You can grab the download links exclusively below.

If you run into any issues or have feature requests, drop a comment down below and let me know how you are using it!

👇 [Download Link Here]

https://www.patreon.com/posts/155993734

About

OmniVoice Portable One-Click Launcher: High-Quality Text-to-Speech & Voice Cloning Software

Topics

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors