Downloads · 30 days
12
24% of all-time downloads
piper-plus-css10-ja-6lang
vokra/piper-plus-css10-ja-6lang
piper-plus-css10-ja-6lang is a text-to-speech model from vokra. Use it when you need text read aloud. It is set up for vokra. The card lists the license as mit.
Text to speech model, converted to the Vokra GGUF format for Vokra, a zero-dependency speech-AI inference runtime.
All-time downloads
51
Public
Repo size
77.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf77.4 MB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- vokra
- License
- mit
- Access
- Public
- Created
- Jul 23, 2026
- Updated
- Jul 23, 2026
- SHA
- 25e963b3
Model card
From the Hugging Face model README
piper-plus-css10-ja-6lang (Vokra GGUF)
Text to speech model, converted to the Vokra GGUF format for Vokra, a zero-dependency speech-AI inference runtime.
This is a conversion, not a new model. The weights are the upstream ones; Vokra re-packages them so its runtime can memory-map them directly. Credit for the model belongs upstream — see Source below.
Files
| File | Size | SHA-256 |
|---|---|---|
piper-plus-ja-restamped.gguf | 73.8 MB | a3a17b9b020ef223efaa28d534271c3439774951c9486b95c5231b70cbe1340c |
Usage
# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o piper-plus-ja-restamped.gguf \
https://huggingface.co/vokra/piper-plus-css10-ja-6lang/resolve/main/piper-plus-ja-restamped.gguf
vokra-cli run --model piper-plus-ja-restamped.gguf --text "こんにちは" --output out.wav
Text input needs a G2P front-end; see the model notes below for which one this voice expects.
Provenance
| Field | Value |
|---|---|
| Architecture | piper-plus-mb-istft-vits2 |
| Tensors | 358 |
| Upstream source | ayutaz/piper-plus (MIT) |
| Upstream licence | MIT |
| Licence class | permissive |
| Registry model id | piper-plus |
| Vokra GGUF schema | 1 |
| Converted by | vokra-core 0.1.0-alpha.0 |
Every row above is read out of this file's own vokra.* metadata, so the card cannot claim something the artifact does not carry.
Licence
The weights are distributed under MIT, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.
Verifying this file
shasum -a 256 piper-plus-ja-restamped.gguf
# expect: a3a17b9b020ef223efaa28d534271c3439774951c9486b95c5231b70cbe1340c
- Task
- Text-to-Speech
- Library
- vokra
- License
- mit
- Created
- Jul 23, 2026
- Updated
- Jul 23, 2026