matxa-tts-v2

matxa-tts-v2

Turns Catalan text into speech with a fast, lightweight voice model for central Catalan. Runs in the browser on Hugging Face, or in a Docker container on your own computer.

Made by BSC-LT 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 text-to-speech demo for central Catalan, built to be fast and light. You give it Catalan text and it produces spoken audio. The repository holds two ONNX model files, speaker lists in JSON and the app code.

Who it suits: It suits people who need a Catalan voice, from developers adding speech output to teachers and content makers.

Industry | Who uses it | How they use it | Example
Software | Developers | Try a Catalan voice before adding speech to an app | A developer listens to sample sentences and checks the sound
Media | Content creators | Turn Catalan text into spoken audio | A creator voices a short script in Catalan
Education | Language teachers | Let learners hear written Catalan read aloud | A teacher plays a text for a class
Research | Speech researchers | Study a fast ONNX-based Catalan synthesis setup | A researcher looks at the model files and the datasets named

You can skip it if you need a language other than Catalan.

Where to use it: You use it in these places.

• A web browser, on the Space's page on Hugging Face
• Docker on Windows, macOS or Linux, for a local copy

Use case | Who | What they get back
Hear Catalan text | Anyone | Spoken audio for the text
Test a voice model | Developers | A working demo to judge the sound and speed
Run it yourself | Developers | A container that serves the app on port 7860

How to set it up: Online use needs only a browser. A local copy needs Python for the download step and Docker for the app.

• A web browser, for the online page
• Python with pip, to fetch the files
• Docker, to build and run the app

1. Open the Space's page on Hugging Face to use it online, with nothing to install.
2. For a local copy, install the Hugging Face Hub package.
3. Download the Space's files into a folder and move into it.
4. Build the Docker image from the Dockerfile.
5. Run the container with port 7860 published, then open that port in your browser.

pip install -U huggingface_hub
hf download BSC-LT/matxa-tts-v2 --repo-type space --local-dir matxa-tts-v2
cd matxa-tts-v2
docker build -t matxa-tts-v2 .
docker run -it -p 7860:7860 matxa-tts-v2

How to use it: Open the Space's page, or the local copy on port 7860, and type some Catalan text into the page. Start the speech and play the audio it returns.

docker run -it -p 7860:7860 matxa-tts-v2

Example: You open the page and enter a short Catalan sentence. The app returns spoken audio of that sentence in central Catalan, which you can play in the browser.

For newcomers and experts: Text-to-speech means a program reads written text aloud. This one speaks central Catalan, and it is meant to run quickly on modest hardware. Start by opening the Space's page and trying a short sentence.

Under the hood, the Space is a Docker app that serves on port 7860 and runs on cpu-basic hardware at Hugging Face. The file names suggest one ONNX model with 10 steps and a multiaccent one with 20 steps, each with its own speaker list. The record also names a 22 kHz vocoder model and two Catalan speech datasets.

You enter Catalan text
The app loads an ONNX speech model
The model synthesizes speech
You play the audio

Good to know: The source says little beyond the one-line description, so check the page itself for voices and limits.

• License: gpl-3.
• Cost to run: none named.
• Data it reaches: the text you enter. The record names the model projecte-aina/alvocat-vocos-22khz and the datasets projecte-aina/festcat_trimmed_denoised and projecte-aina/openslr-slr69-ca-trimmed-denoised.
• Not for: languages other than Catalan, since the description names Catalan only.

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: docker
• License: gpl-3.0

Links

• Space: https://huggingface.co/spaces/BSC-LT/matxa-tts-v2
• Files: https://huggingface.co/spaces/BSC-LT/matxa-tts-v2/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.