Open catalog · Piper TTS
Find the right voice.
Run it anywhere.
Search hundreds of open text-to-speech voices, listen to samples, check where each one comes from, and synthesize speech locally — nothing leaves your device.
Browse by language
Every model is indexed by language. Pick one to open the catalog with that filter applied.
Voices worth hearing
A curated selection of official and community models. Each page has samples, technical details and a local synthesizer.
GLaDOS - French Medium Voice
Siwis - French (FR)
Gilles - French (FR)
Bass - Polish (PL)
Daniela - Spanish (AR)
Libritts - English (US)
Mykyta - Ukrainian (UA)
Oleksa - Ukrainian (UA)
Provenance
Every voice has a source.
Astra - Valorant Piper TTS is linked to the Astra - LJSpeech Dataset dataset. Open both pages to review their repositories and the license of each resource.
Recently updated
Models added or revised most recently.
From recordings to a working voice
Step-by-step guides to prepare a dataset, train a model and use it from the command line, Python or Node.js.
Create an LJSpeech dataset for Piper TTS
LJSpeech is the standard format expected by Piper. Each sentence is a separate WAV file, paired with its transcript in metadata.csv.
Train a voice on Kaggle
Kaggle assigns GPU quota to your account, and the allowance can vary with availability. Check the counter before starting a long session.
Use a Piper voice
Install Piper, get the two files for a voice, and generate a WAV locally. The commands below use the version maintained by the Open Home Foundation.
Use Piper in a Node.js project with pipertts
pipertts brings Piper to Node.js, with file output or in-memory audio. The recommended mode is PiperNativeTTS: fully native in-process inference (ONNX plus a compiled espeak bridge), no Python, roughly 10x faster than the wrapper. Voices (.onnx plus .onnx.json) remain separate files.
Piper Plus voices
Some voices use the Piper Plus architecture: multilingual synthesis, prosody, and MB-iSTFT decoding. They carry the Piper+ badge in the catalogue and require the piper-plus runtime, not the standard piper binary.
Ready to find your voice?
Filter by language, quality, speakers or license, then try any model directly in your browser.