Kokoro TTS

Kokoro TTS

Reads text aloud with the compact Kokoro-82M model on a Gradio page that runs in the browser. For people who want to try this text-to-speech model without installing anything.

Made by hexgrad 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: Kokoro TTS is a Gradio page from hexgrad for trying the Kokoro-82M text-to-speech model. The page notes an upgrade to version 1.0. You can open it in the browser with nothing to install.

Who it suits: It suits people who want to hear what a small open speech model sounds like, and developers who want to read how a TTS demo is put together.

Industry | Who uses it | How they use it | Example
Media | Content creators | Try spoken versions of short scripts | Give it a few lines and play the audio
Education | Teachers and students | Hear written passages read aloud | Paste a short paragraph and listen
Accessibility | Writers | Listen to a draft to catch awkward phrasing | Play back a page of your own text
Software | Python developers | Read a compact Gradio demo for a speech model | Look through app.py

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 longer passages | Students | Speech for sample texts the repository ships, named after two novels
Study the demo | Developers | A small Gradio app of a few files

How to set it up: The online page needs nothing. A local copy needs Python and two lists of packages.

• Python and pip
• Python packages from requirements.txt
• System packages from packages.txt, which the Space installs with apt-get
• Windows, macOS or Linux

1. Install the Hugging Face hub library.
2. Download the Space's files into a folder named Kokoro-TTS.
3. Move into that folder.
4. Install Gradio 5.24.0, then the packages from requirements.txt.
5. Start app.py.

pip install -U huggingface_hub
hf download hexgrad/Kokoro-TTS --repo-type space --local-dir Kokoro-TTS
cd Kokoro-TTS
pip install gradio==5.24.0
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. Give the page some text and ask for 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 text beyond a one-line upgrade note, so the controls are whatever the page itself shows.

The app is built with Gradio 5.24.0, and its main file is app.py. The Hugging Face copy runs on ZeroGPU hardware. The record names one model, Kokoro-82M. The repository also holds en.txt and two markdown files named after the novels Frankenstein and The Great Gatsby. The record does not say how these are used.

Open the page
Give it some text
The Kokoro-82M 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 text, so voices, languages and limits are not described here.
• License: apache-2.
• Cost to run: none named.
• Data it reaches: The text you give it.

On Hugging Face, 13 November 2026

• Likes: 3,556
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/hexgrad/Kokoro-TTS
• Files: https://huggingface.co/spaces/hexgrad/Kokoro-TTS/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.