HolosTTS: Ukrainian text to speech

HolosTTS: Ukrainian text to speech

Reads Ukrainian text aloud in your browser with the HolosTTS model, trained on a Ukrainian dataset with many speakers. Suits creators, teachers and developers working with Ukrainian audio.

Made by patriotyk 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: This Space is a browser demo of HolosTTS, a text-to-speech model for Ukrainian. The model was trained on a Ukrainian dataset that has many speakers. A small Gradio page wraps it and runs on Hugging Face hardware, so you give it text and get audio back.

Who it suits: It suits people who need Ukrainian speech from text, and developers or researchers who want to hear the model before using it. The author keeps the full code on GitHub.

Industry | Who uses it | How they use it | Example
Media | Video and podcast makers | Draft Ukrainian narration from a script | Listen to a short script read aloud
Education | Language teachers | Play Ukrainian sentences for students | Hear a practice sentence spoken
Software | Developers | Read a small app built around the model | Check how the app loads HolosTTS
Research | Speech researchers | Judge Ukrainian output by ear | Compare several sentences by listening

You can skip it if you need languages other than Ukrainian, since this model is built for one language.

Where to use it:

• A web browser: open the Space page on Hugging Face
• Windows, macOS or Linux: run a copy with Python 3.12

Use case | Who | What they get back
Speak Ukrainian text | Content makers | Audio of your text read aloud
Test the model | Researchers | Samples to judge by ear
Run your own copy | Developers | The same app on your own computer

How to set it up: The online page needs nothing. A local copy needs Python 3.12 and the packages in requirements.txt.

• A web browser for the online demo
• Python 3.12 for a local copy
• The packages listed in requirements.txt

1. To use it online, open the Space page on Hugging Face.
2. To run a copy, install the Hugging Face hub package.
3. Download the Space into a local folder.
4. Move into the folder and install Gradio 6.31.0 and the listed packages.
5. Start the app.

pip install -U huggingface_hub
hf download patriotyk/HolosTTS --repo-type space --local-dir HolosTTS
cd HolosTTS
pip install gradio==6.31.0
pip install -r requirements.txt
python app.py

How to use it: Run the app from its folder, or open the Space online. Type the Ukrainian text you want to hear and start generation. The page then plays the audio.

python app.py

Example: You type one short Ukrainian sentence and press the button to generate. The page returns audio of that sentence, which you can play back and judge by ear.

For newcomers and experts: If you are new to this, type one short sentence first. Short input shows you quickly whether the voice and pronunciation suit your needs.

If you know the field, the model was trained on a multispeaker Ukrainian dataset, so its voices come from many speakers. The repository holds the app file, a requirements list and a file named verbalizer.py. The hosted Space runs on Hugging Face's zero-a10g hardware.

You type Ukrainian text
The Gradio app passes it to HolosTTS
The model generates speech
You play the audio

Good to know: The README is short, so the page itself is the guide to its controls. The model handles Ukrainian only.

• License: MIT
• Cost to run: none named
• Data it reaches: the text you type
• Not for: languages other than Ukrainian

On Hugging Face, 13 November 2026

• Likes: 10
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/patriotyk/HolosTTS
• Files: https://huggingface.co/spaces/patriotyk/HolosTTS/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.