← All Piper voices

`en_US-libritts_r-medium`

en_US-libritts_r-medium is a English (English) voice for the Piper engine, and Quick TTS runs it free in your browser with nothing uploaded. This page is the honest version: what tier it is, what sits beneath it when your device cannot load it, what the alternative on English is, and where it falls short.

What this voice actually is

Fact	Value
Voice ID	`en_US-libritts_r-medium`
Engine	Piper, running as WebAssembly in your browser
Language	English (English)
Quality tier	`medium`, the tier Quick TTS treats as the default everywhere, and the best quality-per-megabyte Piper offers
Preselected?	Yes. This is the voice Quick TTS starts on when you choose Piper on English.
Needs a GPU?	No. Piper is the engine that runs without one.
Step-down tier	Yes. `en_US-lessac-low`, a step-down tier only: not selectable, and not in the dropdown. Used automatically on a device that cannot load this model.
Also available in HD?	Yes. Supertonic HD speaks English at 44.1kHz, on WebGPU only.
Integrity	SHA-256 pinned. Weights are rejected unless their hash matches the pin, on every host we fetch from.

What is worth knowing about it

This is the voice Quick TTS preselects when you switch to Piper on English, and it is the most-generated voice on the site by a wide margin, because English is the largest locale and Piper is the plurality engine across every device class.

LibriTTS-R is a restored version of the LibriTTS audiobook corpus, which is why it holds up on long-form reading specifically: it was trained on people reading books aloud for hours, not on short prompted utterances. If you are pointing this at a PDF or a chapter rather than a sentence, that is the reason to keep the default.

The other English Piper voices

English ships 3 selectable Piper voices, so this one is a choice rather than the only option:

What happens when your device cannot load it

Piper's real failure mode is memory, not speed. The model has to allocate an ONNX session, and on weak or GPU-less hardware that allocation is the thing that fails. Quick TTS handles it in two layers, and both are automatic:

Before the download. A device reporting 4GB of memory or less starts on the smallest available tier instead of the default, so it never pulls the large model only to fail on it. Below 2GB, Piper is hidden entirely rather than offered and then failing.
After a failure. If this model will not allocate, Quick TTS steps down automatically to en_US-lessac-low — a step-down tier, not selectable and not in the dropdown. You cannot choose it by name; it exists only as the automatic landing place when this voice fails.

How to use it

Open quick-tts.com, switch the engine dropdown to Piper, and choose en_US-libritts_r-medium from the voice list. The neural voice list follows the page language, so English voices appear on the English page. Speed, volume and voice can all be changed mid-read and the current passage replays under the new settings without starting over. Switching the engine itself stops playback, so you press play once to start the new one. There is no mid-read handover of the remaining text between engines.

The first play click downloads the model once and caches it; afterwards it starts immediately and keeps working offline.

Nothing you paste is uploaded

Piper runs as WebAssembly inside your own browser tab. The model is downloaded once and cached; after that, the text you paste is turned into audio on your machine and never sent anywhere. That is an architectural property rather than a policy promise: the test is that generation keeps working with your network disconnected once the model has loaded.

Common questions

What is en_US-libritts_r-medium?

It is a English neural text-to-speech voice for the Piper engine, at the medium quality tier. Quick TTS runs it as WebAssembly inside your browser, so it needs no GPU and no account, and the text you paste is never uploaded.

Is en_US-libritts_r-medium free?

Yes. There is no account, no character limit and no watermark. The model downloads once to your browser and then runs on your own device, so there is no per-character server cost to meter.

Do I need a GPU to use en_US-libritts_r-medium?

No. Piper runs on WebAssembly and works on machines with no usable GPU at all, which is why it is the most-selected engine here. The GPU-only alternative on English is Supertonic HD.

How do I select en_US-libritts_r-medium in Quick TTS?

Open quick-tts.com, switch the engine dropdown to Piper, and pick it from the voice list. The neural voice list follows the page language, so you need the English page to see English voices.

Can I download the audio from en_US-libritts_r-medium?

Yes, as WAV or MP3, generated on your device. Anything past roughly 20,000 characters is packaged as a ZIP of audio parts so that memory stays bounded on long documents.

en_US-libritts_r-medium