Licenses & Attribution

This page contains attribution for the voices/datasets (TTS) used in the app. Update it as you add new voices.

Piper TTS — voices (attribution examples)

Third‑party notices

Voice: en_US-libritts-high (Piper)
Dataset source: LibriTTS (OpenSLR SLR60) — http://www.openslr.org/60/
License: Creative Commons Attribution 4.0 International (CC BY 4.0) — https://creativecommons.org/licenses/by/4.0/
Voice: en_GB-alba-medium (Piper)
Dataset source: https://datashare.ed.ac.uk/handle/10283/3270
License: CC BY 4.0 — https://creativecommons.org/licenses/by/4.0/
Voice: en_GB-aru-medium (Piper)
Dataset source: https://www.liverpool.ac.uk/architecture/research/acoustics-research-unit/speech-corpus/
License: CC BY 4.0 — https://creativecommons.org/licenses/by/4.0/
Voice/Dataset: Jenny (Jenny TTS Dataset)
Download: https://www.languagereactor.com/dataset.tar.zst
License: Custom (attribution required in software/websites/interfaces that generate audio: call the voice “Jenny” and where practical “Jenny (Dioco)”. Commercial use permitted.)
Voice: ru_RU-irina-medium (RHVoice)
Source: https://github.com/RHVoice/RHVoice
License: CC BY-SA 4.0 — https://creativecommons.org/licenses/by-sa/4.0/
Voice/Dataset: OpenSLR SLR83
Source: http://www.openslr.org/83/
License: CC BY-SA 4.0 — https://creativecommons.org/licenses/by-sa/4.0/
Voice: fa_IR-gyro-medium (Piper)
Dataset source: Persian TTS Male VITS (Kamtera) — https://github.com/gyroing
Source: https://huggingface.co/rhasspy/piper-voices/tree/main/fa/fa_IR/gyro/medium
License: See source (no specific license specified)
Voice: fr_FR-mls-medium (Piper)
Dataset source: Multilingual LibriSpeech (OpenSLR SLR94) — http://openslr.org/94/
License: CC BY 4.0 — https://creativecommons.org/licenses/by/4.0/
Voice: fr_FR-siwis-medium (Piper)
Dataset source: SIWIS French Speech Synthesis Database — https://datashare.is.ed.ac.uk/handle/10283/2353
License: CC BY 4.0 — https://creativecommons.org/licenses/by/4.0/
Voice: it_IT-riccardo-x_low (Piper)
Dataset source: M-AILABS Speech Dataset — https://www.caito.de/2019/01/03/the-m-ailabs-speech-dataset/
License: Custom (M-AILABS) — Commercial use allowed
Voice: de_DE-kerstin-low (Piper)
Dataset source: Kerstin Voice Dataset — https://github.com/rhasspy/dataset-voice-kerstin
License: CC0 (Public Domain) — https://creativecommons.org/publicdomain/zero/1.0/
Voice: de_DE-thorsten-high (Piper)
Dataset source: Thorsten Voice — https://github.com/thorstenMueller/Thorsten-Voice
License: CC0 (Public Domain) — https://creativecommons.org/publicdomain/zero/1.0/
Voice: de_DE-emotion-medium (Piper)
Dataset source: Thorsten Voice (emotions) — https://github.com/thorstenMueller/Thorsten-Voice
License: CC0 (Public Domain) — https://creativecommons.org/publicdomain/zero/1.0/
Voice: ar_JO-kareem-medium (Piper)
Dataset source: Arabic TTS Train — https://github.com/AliMokhammad/arabicttstrain/
License: See source (no specific license specified)
Voice: pt_PT-tugao-medium (Piper)
Dataset source: OHF-Voice (Home Assistant) — https://github.com/OHF-Voice/voice-datasets
License: CC0 (Public Domain) — https://creativecommons.org/publicdomain/zero/1.0/
Voice: pt_BR-facula-medium (Piper)
Dataset source: OHF-Voice (Home Assistant) — https://github.com/OHF-Voice/voice-datasets
License: CC0 (Public Domain) — https://creativecommons.org/publicdomain/zero/1.0/

Note: if you modified the model/package, add “Modified” and the date.

How to add a new voice

Checklist

Open the voice’s MODEL_CARD and find License and URL.
If it says See LICENSE file, locate the corresponding LICENSE (locally / in the source repo).
Add a line to this list: voice name → source → license link.

Piper TTS — голоса (пример атрибуции)

Third‑party notices

Голос: en_US-libritts-high (Piper)
Источник датасета: LibriTTS (OpenSLR SLR60) — http://www.openslr.org/60/
Лицензия: Creative Commons Attribution 4.0 International (CC BY 4.0) — https://creativecommons.org/licenses/by/4.0/
Голос: ru_RU-irina-medium (RHVoice)
Источник: https://github.com/RHVoice/RHVoice
Лицензия: CC BY-SA 4.0 — https://creativecommons.org/licenses/by-sa/4.0/
Голос: en_GB-alba-medium (Piper)
Источник датасета: https://datashare.ed.ac.uk/handle/10283/3270
Лицензия: CC BY 4.0 — https://creativecommons.org/licenses/by/4.0/
Голос: en_GB-aru-medium (Piper)
Источник датасета: https://www.liverpool.ac.uk/architecture/research/acoustics-research-unit/speech-corpus/
Лицензия: CC BY 4.0 — https://creativecommons.org/licenses/by/4.0/
Голос/датасет: Jenny (Jenny TTS Dataset)
Ссылка: https://www.languagereactor.com/dataset.tar.zst
Лицензия: нестандартная (нужна атрибуция в софте/сайтах/интерфейсах, которые генерируют аудио: называть голос “Jenny” и по возможности “Jenny (Dioco)”. Коммерческое использование разрешено.)
Голос/датасет: OpenSLR SLR83
Источник: http://www.openslr.org/83/
Лицензия: CC BY-SA 4.0 — https://creativecommons.org/licenses/by-sa/4.0/
Голос: fa_IR-gyro-medium (Piper)
Источник датасета: Persian TTS Male VITS (Kamtera) — https://github.com/gyroing
Источник: https://huggingface.co/rhasspy/piper-voices/tree/main/fa/fa_IR/gyro/medium
Лицензия: см. источник (лицензия не указана)
Голос: fr_FR-mls-medium (Piper)
Источник датасета: Multilingual LibriSpeech (OpenSLR SLR94) — http://openslr.org/94/
Лицензия: CC BY 4.0 — https://creativecommons.org/licenses/by/4.0/
Голос: fr_FR-siwis-medium (Piper)
Источник датасета: SIWIS French Speech Synthesis Database — https://datashare.is.ed.ac.uk/handle/10283/2353
Лицензия: CC BY 4.0 — https://creativecommons.org/licenses/by/4.0/
Голос: it_IT-riccardo-x_low (Piper)
Источник датасета: M-AILABS Speech Dataset — https://www.caito.de/2019/01/03/the-m-ailabs-speech-dataset/
Лицензия: Собственная (M-AILABS) — коммерческое использование разрешено
Голос: de_DE-kerstin-low (Piper)
Источник датасета: Kerstin Voice Dataset — https://github.com/rhasspy/dataset-voice-kerstin
Лицензия: CC0 (Public Domain) — https://creativecommons.org/publicdomain/zero/1.0/
Голос: de_DE-thorsten-high (Piper)
Источник датасета: Thorsten Voice — https://github.com/thorstenMueller/Thorsten-Voice
Лицензия: CC0 (Public Domain) — https://creativecommons.org/publicdomain/zero/1.0/
Голос: de_DE-emotion-medium (Piper)
Источник датасета: Thorsten Voice (emotions) — https://github.com/thorstenMueller/Thorsten-Voice
Лицензия: CC0 (Public Domain) — https://creativecommons.org/publicdomain/zero/1.0/
Голос: ar_JO-kareem-medium (Piper)
Источник датасета: Arabic TTS Train — https://github.com/AliMokhammad/arabicttstrain/
Лицензия: см. источник (лицензия не указана)

Примечание: если вы модифицировали модель/пак, добавьте пометку “Modified/Изменено” и дату.

Как добавить новый голос

Checklist

Открой MODEL_CARD голоса и найди License и URL.
Если написано See LICENSE file — найди соответствующий LICENSE (локально/в источнике).
Добавь строку в этот список: имя голоса → источник → ссылка на лицензию.