OmniVoice

OmniVoice

Clones a voice and speaks text in it across more than 600 languages, on a Gradio page that runs in the browser. For people who want to try voice cloning text-to-speech.

Made by k2-fsa on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: OmniVoice is a Gradio page from the k2-fsa team for voice-cloning text-to-speech. Its tagline says it covers more than 600 languages. You can open it in the browser with nothing to install.

Who it suits: It suits people who want to hear how voice cloning sounds across many languages, and developers who want to read how such a demo is built.

Industry | Who uses it | How they use it | Example
Media | Content creators | Try spoken versions of short scripts | Give it a line of text and play the audio
Localisation | Language teams | Hear text in many languages | Try a language you rarely hear
Research | Speech researchers | Look at a voice cloning system in action | Run one sentence through the page
Software | Python developers | Study the demo and its omnivoice package | Read app.py and the omnivoice folder

Skip it if you need a finished voice product with support, since this is a demo page.

Where to use it:

• A web browser, on the Space's page at Hugging Face, which runs on ZeroGPU
• Your own Windows, macOS or Linux computer with Python

Use case | Who | What they get back
Hear text read aloud | Creators | Generated speech for the text you give it
Try cloning a voice | Researchers | Speech in a voice taken from a sample
Study the demo | Developers | A Gradio app and the package behind it

How to set it up: The online page needs nothing. A local copy needs Python and the packages in requirements.txt.

• Python and pip
• Python packages from requirements.txt
• Windows, macOS or Linux

1. Install the Hugging Face hub library.
2. Download the Space's files into a folder named OmniVoice.
3. Move into that folder.
4. Install Gradio 6.10.0, then the packages from requirements.txt.
5. Start app.py.

pip install -U huggingface_hub
hf download k2-fsa/OmniVoice --repo-type space --local-dir OmniVoice
cd OmniVoice
pip install gradio==6.10.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space's page, or run the last command above for a local copy and open the address it prints. Then use the form the page shows to make speech.

python app.py

Example: You open the page, give it a short sentence and ask for speech. The page runs the model and returns audio you can play in the browser.

For newcomers and experts: Try one short sentence first and listen to the result. The record has no README, so the controls are whatever the page itself shows.

The app is built with Gradio 6.10.0, and its main file is app.py. The Hugging Face copy runs on ZeroGPU hardware. The record names five models, including OmniVoice itself, a Higgs audio tokenizer, Whisper large v3 turbo, Qwen3 0.6B and a set of TTS evaluation models. It does not say what part each one plays.

Open the page
Give it text and a voice sample
The OmniVoice model runs on a ZeroGPU
Play the audio

Good to know:

• Hardware: The Hugging Face copy runs on ZeroGPU hardware.
• Gaps: The source has no README, so voice options, limits and the language list are not described here.
• License: apache-2.
• Cost to run: none named.
• Data it reaches: The text and any voice sample you give it.

On Hugging Face, 13 November 2026

• Likes: 1,463
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/k2-fsa/OmniVoice
• Files: https://huggingface.co/spaces/k2-fsa/OmniVoice/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.