Downloads · 30 days
15
100% of all-time downloads
piper-voices
echo-dust/piper-voices
piper-voices is a text-to-speech model from echo-dust. Use it when you need text read aloud. It is set up for piper. The card lists the license as other.
A pinned subset of diffusionstudio/piper-voices (itself a mirror of rhasspy/piper-voices), kept under this account so the app that loads it controls versioning. Files are unchanged; the directory layout is the upstrea…
All-time downloads
15
Public
Repo size
310 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx310 MB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- piper
- License
- other
- Access
- Public
- Created
- Sep 20, 2026
- Updated
- Sep 20, 2026
- SHA
- f2056501
Model card
From the Hugging Face model README
Piper voices — mirror for the Reader PWA
A pinned subset of diffusionstudio/piper-voices
(itself a mirror of rhasspy/piper-voices),
kept under this account so the app that loads it controls versioning. Files are unchanged;
the directory layout is the upstream one, so @mintplex-labs/piper-tts-web resolves paths
the same way. voices.json is the upstream file filtered to the voices present here.
| voice | files | size |
|---|---|---|
en_US-amy-medium | en/en_US/amy/medium/ | 63 MB |
en_US-hfc_female-medium | en/en_US/hfc_female/medium/ | 63 MB |
en_US-ryan-high | en/en_US/ryan/high/ | 121 MB |
en_GB-alan-medium | en/en_GB/alan/medium/ | 63 MB |
Each voice directory carries its upstream MODEL_CARD with the training dataset and its
licence; those terms apply per voice. Piper itself is MIT
(rhasspy/piper).
Mirrored 2026-09-20.
- Task
- Text-to-Speech
- Library
- piper
- License
- other
- Created
- Sep 20, 2026
- Updated
- Sep 20, 2026