Brindille

Brindille

Speaks French text aloud in your browser with a tiny 94K-parameter model, running entirely on your own device in the Estelle voice. It suits people who want French speech with no server and no install.

Made by edbrdi 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: Brindille is a French text-to-speech model with 94K parameters that runs entirely inside the browser. Its inference engine, Alkove, is compiled to WebAssembly. The voice is Estelle, taken from Kyutai's Pocket TTS, and the page's own subtitle says the whole French voice fits in 2.7 MB.

Who it suits: It suits people who want a French voice with no server to run, and developers who want to see a speech model packaged for the browser.

Industry | Who uses it | How they use it | Example
Web development | Front-end developers | Study how a speech model runs in the browser through WebAssembly | A developer reads tts.js and tts.wasm to see how they fit together.
Content creation | Makers of French content | Hear French text read aloud in a clear voice | A maker types a line and listens to the Estelle voice.
Education | French learners and teachers | Listen to sentences read aloud | A learner plays back a sentence several times.
Accessibility | Readers who prefer listening | Have French text spoken without installing anything | A reader opens the page and plays a paragraph.

If you need other languages or voices, skip it, since it offers one French voice.

Where to use it:

• A web browser, through the Space's page on Hugging Face
• Any browser on Windows, macOS or Linux, opening a downloaded copy of index.html

Use case | Who | What they get back
Hear French speech online | Anyone | Audio made in the browser, with nothing to install
Keep a local copy | Developers | The page, the model folder and the WebAssembly files in one folder
Study the packaging | Engineers | tts.js, tts.wasm and the model folder

How to set it up:

• A web browser
• Python and pip, only for the download step

1. Install the huggingface_hub package.
2. Download the Space into a local folder named brindille.
3. Move into that folder.
4. Open index.html in your web browser.

pip install -U huggingface_hub
hf download edbrdi/brindille --repo-type space --local-dir brindille
cd brindille

How to use it: Open the Space's page, or open the downloaded index.html file in your browser. Give the page a French text and play the speech it makes.

Tool | What it does
index.html | The page that you open in the browser
tts.js | The script that runs the speech engine
tts.wasm | The WebAssembly build of the inference engine, going by its name
model | The folder that holds the voice model

Example: You open the page and give it a short French sentence. The browser speaks it in the Estelle voice, and the speech is made on your own device.

For newcomers and experts: If you are new, open the Space's page and try one short sentence. Nothing is installed and no server is involved.

If you know the field, the model is tiny at 94K parameters, and the Alkove inference engine is compiled to WebAssembly. The voice is from Kyutai's Pocket TTS. The repository also carries a NOTICE file with credits.

Open the page in a browser
Give it French text
The WebAssembly engine runs the model
Speech plays on your device

Good to know:

• It runs entirely in the browser, so the speech is made on your own device
• It offers a single French voice
• License: apache-2
• Cost to run: none named
• Data it reaches: only the files in its own folder

On Hugging Face, 13 November 2026

• Likes: 4
• Built with: static
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/edbrdi/brindille
• Files: https://huggingface.co/spaces/edbrdi/brindille/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.