piper-voices

piper-voices

Ready-made voices for the Piper text to speech system, for developers and makers who want their own software to read text aloud.

Made by rhasspy on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: Piper voices is a collection of voice files for Piper, a text to speech system. A voice is what lets Piper turn written text into spoken audio. This repository holds the voices, and the checkpoints for training your own voices sit in a separate repository called piper-checkpoints.

Who it suits: It suits people who want a speech voice that runs through Piper, such as developers adding spoken output to an app or makers giving a project a voice. The record lists language tags such as ar, ca, cs, cy, da, de, el and en.

Industry | Who uses it | How they use it | Example
Software | App developers | Add spoken output to an app | Reading a status message aloud
Accessibility | Tool builders | Give written content a spoken form | Reading a document aloud
Education | Course makers | Turn lesson text into audio | Narrating a short lesson
Hobby projects | Makers | Give a home project a voice | A device that speaks its alerts

Skip it if you do not plan to run Piper yourself.

Where to use it:

• Piper, the text to speech system the voices are made for
• Windows, macOS or Linux, with Python for the download steps
• Your own terminal, for the download command

Use case | Who | What they get back
Spoken output in an app | Developers | Text read aloud in the voice they chose
Training a new voice | Voice builders | A pointer to the separate checkpoints repository

How to set it up: You need a few things in place first.

• Python on Windows, macOS or Linux
• Piper, the system these voices are made for

1. Install the Hugging Face hub package with pip.
2. Download the repository files with the hf command.
3. Choose the voice files you want from the downloaded folder and use them with Piper.

pip install -U huggingface_hub
hf download rhasspy/piper-voices

How to use it: The download command fetches the voice files onto your computer. After that, you give Piper the voice you picked. The model card does not list Piper's own commands, so check Piper's documentation for running it.

hf download rhasspy/piper-voices

Example: You run the download command and wait for it to finish. Your computer now holds the voice files from the repository. You pick one for your language and hand it to Piper, which then reads your text aloud in that voice.

For newcomers and experts: A voice is a set of files that Piper loads in order to speak. Start small. Run the two setup commands and look at the folders that arrive, then choose one voice to try.

The repository is a place to get finished Piper voices, kept apart from the training checkpoints. If you want a new voice instead of an existing one, the training route starts from the piper-checkpoints repository. The record also shows 38 quantized and 5 fine-tuned versions made by other people.

Choose a voice in the repository
Download the files with hf
Load the voice in Piper
Piper reads your text aloud

Good to know:

• License: MIT
• Cost to run: none named
• Data it reaches: it downloads files from Hugging Face onto your computer
• Not for: training new voices, which uses the separate checkpoints repository

On Hugging Face, 13 November 2026

• Downloads in the last 30 days: 0
• Likes: 877
• License: mit
• Languages: ar, ca, cs, cy, da, de, el, en
• Quantized versions: 38
• Fine-tunes: 5
• Tags: onnx

Links

• Model: https://huggingface.co/rhasspy/piper-voices
• Files: https://huggingface.co/rhasspy/piper-voices/tree/main

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download rhasspy/piper-voices

Then follow the usage in its model card. Nothing in this kit runs by itself.