voaice
The voice of an AI, written down and checkable. voaice is the voice stack of mindX: speech in, speech out, measured throughout. It gives a machine a voice, says the realm's names the way their owners say them, and proves which voice made a recording.
This repository is voaice's voice library: 70 open-licensed Piper voices in 29 language families (4.62 GB), kept here so a mindX node holds only the voices it speaks with and fetches any other on demand.
Free for anyone to use
The voices in piper/ are here for anyone to use: download one, run it with
Piper, build on it. Each voice keeps its own open licence, the licence of the
dataset its speakers recorded, and the folder's official licences list every voice under its
licence with a link to the legal code. They are Piper's voices, not ours: credit Piper and the dataset named in
each voice's MODEL_CARD.
What voaice is
| part | what it does | code |
|---|---|---|
| the stack | in-house DSP, torch-free neural TTS and zero-shot cloning, a non-destructive editor, quality-tiered WAV/OGG export, the /voicey surface |
Professor-Codephreak/voaice |
| identity | a .voaice is a voice's identity card: model, measurements, and an 18-decimal vprint (eight acoustic metrics, SHA-256/512, uint256) that Python and the browser compute identically |
cryptoAGI/voaice |
| pronunciation | one respelling table every engine applies to the text it speaks: realm names, then the bankML register (scientific, technical, financial), each entry measured with espeak-ng and versioned | PRONUNCIATION.md |
| OVERLORD | the voice of the OVERLORD: two neural voices in unison, aligned frame by frame (DTW + WSOLA, residual lag 0–10 ms), with an octave and a fifth below, presence harmonics and a diffuse hall without a single echo | hear v3 |
| this library | the open piper voices, unchanged, with their licences and cards | here |
voaice is the voice peer of faicey (the face); with a
.persona they compose aivatar, a person's AI model that looks,
speaks and thinks. Staged together the suite is ollywoo, the Hollywood of AI avatars, inside the
DeltaVerse, where irecto (the director) deploys the finished personas.
Hear it
- rage.pythai.net: every article read aloud from pre-rendered audio. Press LISTEN for the audio deck; OVERLORD of the DeltaVerse opens in the OVERLORD voice, and Three readers, one voice explains the readers.
- playdocs: any document read in any voice of the cast, with a voice studio, a waveform editor and device rendering. A voice your machine can speak as itself is synthesised and encoded on your own processor, inside a budget you set (processor, memory and graphics, 0–100 % to 18 decimals); the host renders the rest.
- deltaverse.pythai.net/voices: the cast · /listen: the reader.
- The render ledger: every rendered article, measured — duration against word count, bytes against duration, said right or said wrong.
Use a voice
from huggingface_hub import hf_hub_download
onnx = hf_hub_download("PYTHAI/voaice", "piper/en_US/ryan/high/en_US-ryan-high.onnx")
cfg = hf_hub_download("PYTHAI/voaice", "piper/en_US/ryan/high/en_US-ryan-high.onnx.json")
# echo "Hello" | piper --model <onnx> --output_file out.wav
Or with voaice's own fetcher, which refuses any voice not classed open and checks every file's md5:
python3 voaice/scripts/piper_voices_hub.py fetch en_US-ryan-high.
Attribution: these voices are Piper's
Every voice here was trained and published by the Piper project and its contributors:
rhasspy/piper (Michael Hansen and contributors; Piper is MIT-licensed). They
are redistributed unchanged from rhasspy/piper-voices. Each voice keeps the licence of the
dataset its speakers recorded, and the original MODEL_CARD (dataset, licence, training notes) sits beside every
model exactly as upstream ships it. When you use a voice, credit the dataset named in its card and Piper.
See LICENSE.md (licences grouped) and NOTICE.
Only open licences, and why most English voices are missing
Of the 177 voices in the upstream catalogue, a voice is carried here only if both its own licence and, when it is "fine-tuned from" another voice, its parent's are open: CC0, public domain, CC BY, CC BY-SA, Apache-2.0, MIT, Unlicense or GPL/AGPL. The following are left out:
- non-commercial voices (CC BY-NC);
- the lessac / CSTR Blizzard 2013 research-only voices, and every voice fine-tuned from lessac, which is most of the English ones;
- voices whose licence reads only "See URL" or "Unknown".
The full classification of all 177 voices, with the licence text each decision was read from, is
piper-voices.json. Copyleft voices (GPL, AGPL, CC BY-SA) keep their share-alike terms in
anything built from them. If a classification is wrong, or you hold an excluded voice whose terms allow
redistribution, open a discussion.
The voices
English 11 · Dutch 7 · French 5 · Spanish 5 · Ukrainian 5 · German 4 · Kazakh 3 · Basque 2 · Catalan 2 · Farsi 2 · Greek 2 · Italian 2 · Swedish 2 · Telugu 2 · Urdu 2 · Armenian 1 · Bengali 1 · Chinese 1 · Czech 1 · Estonian 1 · Finnish 1 · Latvian 1 · Lithuanian 1 · Marathi 1 · Nepali 1 · Norwegian 1 · Polish 1 · Portuguese 1 · Slovenian 1
piper/<locale>/<voice>/<quality>/ holds <key>.onnx, <key>.onnx.json and MODEL_CARD: the upstream tree minus
the language-family directory, every file matching the md5 upstream publishes in voices.json.
| voice | language | quality | speakers | licence (from the card) | upstream |
|---|---|---|---|---|---|
bn_BD-google-medium |
Bengali | medium | 16 | Attribution-ShareAlike 4.0 International | card |
ca_ES-upc_ona-x_low |
Catalan | x_low | 1 | CC BY-SA 3.0 ES | card |
ca_ES-upc_pau-x_low |
Catalan | x_low | 1 | CC BY-SA 3.0 ES | card |
cs_CZ-kasandra-medium |
Czech | medium | 1 | Creative Commons Attribution 4.0 International (CC BY 4.0) | card |
de_DE-kerstin-low |
German | low | 1 | CC0 | card |
de_DE-mls-medium |
German | medium | 236 | CC-BY 4.0 | card |
de_DE-thorsten-low |
German | low | 1 | CC0 | card |
de_DE-thorsten_emotional-medium |
German | medium | 8 | CC0 | card |
el_GR-rapunzelina-low |
Greek | low | 1 | CC0 | card |
el_GR-rapunzelina-medium |
Greek | medium | 1 | CC0 | card |
en_GB-cori-high |
English | high | 1 | public domain | card |
en_GB-cori-medium |
English | medium | 1 | public domain | card |
en_GB-southern_english_female-low |
English | low | 1 | CC-BY-SA 4.0 International | card |
en_US-bryce-medium |
English | medium | 1 | public domain | card |
en_US-john-medium |
English | medium | 1 | public domain | card |
en_US-kathleen-low |
English | low | 1 | CC0 | card |
en_US-kristin-medium |
English | medium | 1 | public domain | card |
en_US-libritts-high |
English | high | 904 | CC BY 4.0 | card |
en_US-ljspeech-high |
English | high | 1 | public domain | card |
en_US-ljspeech-medium |
English | medium | 1 | public domain | card |
en_US-norman-medium |
English | medium | 1 | public domain | card |
es_ES-carlfm-x_low |
Spanish | x_low | 1 | Public domain | card |
es_ES-mls_10246-low |
Spanish | low | 1 | CC BY 4.0 | card |
es_ES-mls_9972-low |
Spanish | low | 1 | CC BY 4.0 | card |
es_MX-ald-medium |
Spanish | medium | 1 | http://unlicense.org | card |
es_MX-claude-high |
Spanish | high | 1 | apache-2.0 | card |
et_EE-news-medium |
Estonian | medium | 4 | CC-BY (META-SHARE "Available - Unrestricted Use") | card |
eu_ES-antton-medium |
Basque | medium | 1 | Creative Commons Attribution 4.0 | card |
eu_ES-maider-medium |
Basque | medium | 1 | Creative Commons Attribution 4.0 | card |
fa_IR-ganji-medium |
Farsi | medium | 1 | CC0 | card |
fa_IR-ganji_adabi-medium |
Farsi | medium | 1 | CC0 | card |
fi_FI-harri-low |
Finnish | low | 1 | CC0 | card |
fr_FR-gilles-low |
French | low | 1 | CC0 | card |
fr_FR-mls-medium |
French | medium | 125 | CC-BY 4.0 | card |
fr_FR-mls_1840-low |
French | low | 1 | CC BY 4.0 | card |
fr_FR-siwis-low |
French | low | 1 | CC-BY 4.0 | card |
fr_FR-tom-medium |
French | medium | 1 | AGPLv3 | card |
hy_AM-gor-medium |
Armenian | medium | 1 | GPL 2.0 | card |
it_IT-serena-high |
Italian | high | 1 | CC-BY-4.0 | card |
it_IT-serena-medium |
Italian | medium | 1 | CC-BY-4.0 | card |
kk_KZ-iseke-x_low |
Kazakh | x_low | 1 | CC-BY-4.0 | card |
kk_KZ-issai-high |
Kazakh | high | 6 | CC-BY-4.0 | card |
kk_KZ-raya-x_low |
Kazakh | x_low | 1 | CC-BY-4.0 | card |
lt_LT-reginute1-medium |
Lithuanian | medium | 1 | CC-BY-4.0 | card |
lv_LV-aivars-medium |
Latvian | medium | 1 | CC0 1.0 Universal | card |
mr_IN-google-medium |
Marathi | medium | 9 | Attribution-ShareAlike 4.0 International | card |
ne_NP-google-x_low |
Nepali | x_low | 18 | CC-BY-SA-4.0 International | card |
nl_BE-nathalie-x_low |
Dutch | x_low | 1 | CC0 | card |
nl_BE-rdh-medium |
Dutch | medium | 1 | CC0 1.0 Universal | card |
nl_BE-rdh-x_low |
Dutch | x_low | 1 | CC0 1.0 Universal | card |
nl_NL-alex-medium |
Dutch | medium | 1 | CC0 | card |
nl_NL-mls-medium |
Dutch | medium | 52 | CC-BY 4.0 | card |
nl_NL-mls_5809-low |
Dutch | low | 1 | CC BY 4.0 | card |
nl_NL-mls_7432-low |
Dutch | low | 1 | CC BY 4.0 | card |
no_NO-nvcc-medium |
Norwegian | medium | 10 | CC0 | card |
pl_PL-mls_6892-low |
Polish | low | 1 | CC BY 4.0 | card |
pt_BR-edresson-low |
Portuguese | low | 1 | CC BY 4.0 | card |
sl_SI-artur-medium |
Slovenian | medium | 1 | https://creativecommons.org/licenses/by/4.0/ | card |
sv_SE-alma-medium |
Swedish | medium | 1 | The model weights are released under CC BY 4.0, following the license | card |
sv_SE-nst-medium |
Swedish | medium | 1 | CC0 | card |
te_IN-padmavathi-medium |
Telugu | medium | 1 | CC-BY-4.0 | card |
te_IN-venkatesh-medium |
Telugu | medium | 1 | CC-BY-4.0 | card |
uk_UA-lada-x_low |
Ukrainian | x_low | 1 | Apache 2.0 | card |
uk_UA-mykyta-high |
Ukrainian | high | 1 | Apache 2.0 | card |
uk_UA-oleksa-high |
Ukrainian | high | 1 | Apache 2.0 | card |
uk_UA-tetiana-high |
Ukrainian | high | 1 | Apache 2.0 | card |
uk_UA-ukrainian_tts-medium |
Ukrainian | medium | 3 | CC0 | card |
ur_PK-aegis_female-medium |
Urdu | medium | 1 | mit | card |
ur_PK-fasih-medium |
Urdu | medium | 1 | mit | card |
zh_CN-chaowen-medium |
Chinese | medium | 1 | CC0 | card |
- Downloads last month
- -