Back to Home

Credits

Open-source software and models used by LINGUAE, with their licenses.

Updated October 11, 2026

Linguae uses open-source software and models published by third parties. We thank them. This page lists, for each one, its author, license and source, as those licenses require. Each license applies only to the component concerned: the rest of Linguae (its code, design and brand) is not distributed under an open-source license and remains governed by the Terms of Service.

Translation and review models

These models are not included in the installer: the application downloads them from Hugging Face when you choose them, then runs them on your device. The technical names below are given for the attribution their licenses require.

Engine in LinguaeModel (author)LicenseSource
StandardOPUS-MT, 1,190 language pairs (Language Technology Research Group at the University of Helsinki, OPUS-MT project), trained with Marian NMTApache 2.0 for 1,187 pairs; CC BY 4.0 for opus-mt-en-de, opus-mt-ru-en and opus-mt-zh-enhttps://huggingface.co/Helsinki-NLP
PremiumM2M-100, 418M and 1.2B (Meta AI)MIThttps://huggingface.co/facebook/m2m100_418M
Premium (second engine)MADLAD-400 3B MT (Google)Apache 2.0https://huggingface.co/google/madlad400-3b-mt
Deep Review (Pro)Qwen2.5-7B-Instruct, 4-bit MLX conversion by mlx-community (Alibaba Cloud)Apache 2.0https://huggingface.co/mlx-community/Qwen2.5-7B-Instruct-4bit
Deep Review, lite version (Pro)Qwen3-4B-Instruct-2507, 4-bit MLX conversion by mlx-community (Alibaba Cloud)Apache 2.0https://huggingface.co/mlx-community/Qwen3-4B-Instruct-2507-4bit

The model licenses apply to you when you download and use the models. All those listed here (Apache 2.0, MIT, CC BY 4.0) allow commercial use.

To cite OPUS-MT: Tiedemann, J. and Thottingal, S. (2020), "OPUS-MT, Building open translation services for the World", Proceedings of EAMT 2020. For M2M-100: Fan, A. et al. (2021), "Beyond English-Centric Multilingual Machine Translation", Journal of Machine Learning Research 22(107).

Runtime environment (installed on your device at first launch)

ComponentLicenseSource
Transformers, huggingface_hub (Hugging Face)Apache 2.0https://github.com/huggingface/transformers
PyTorchBSD-3-Clause and compatible licenses (see the project)https://pytorch.org
MLX and mlx-lm (Apple, macOS Apple Silicon only)MIThttps://github.com/ml-explore/mlx-lm
bitsandbytes (non-macOS)MIThttps://github.com/bitsandbytes-foundation/bitsandbytes
SentencePieceApache 2.0https://github.com/google/sentencepiece
sacremosesMIThttps://github.com/hplt-project/sacremoses
FastAPIMIThttps://fastapi.tiangolo.com
UvicornBSD-3-Clausehttps://www.uvicorn.org
PydanticMIThttps://docs.pydantic.dev
python-docx, python-pptx, openpyxlMIThttps://github.com/python-openxml/python-docx, https://github.com/scanny/python-pptx, https://foss.heptapod.net/openpyxl/openpyxl
pdfplumberMIThttps://github.com/jsvine/pdfplumber
pypdfium2 (PDFium)BSD-3-Clause or Apache 2.0https://github.com/pypdfium2-team/pypdfium2
pypdfBSD-3-Clausehttps://github.com/py-pdf/pypdf
pikepdfMPL-2.0https://github.com/pikepdf/pikepdf
ReportLabBSD-3-Clausehttps://www.reportlab.com
charset-normalizerMIThttps://github.com/jawah/charset_normalizer
psutilBSD-3-Clausehttps://github.com/giampaolo/psutil

Desktop application

ComponentLicenseSource
Electron (and Chromium, whose notices ship with the application)MIThttps://www.electronjs.org
React, React DOMMIThttps://react.dev
React RouterMIThttps://reactrouter.com
Framer MotionMIThttps://www.framer.com/motion
i18next, react-i18next, i18next-browser-languagedetectorMIThttps://www.i18next.com
react-hot-toastMIThttps://react-hot-toast.com
HeroiconsMIThttps://heroicons.com
LucideISChttps://lucide.dev
AxiosMIThttps://axios-http.com
electron-store, electron-updaterMIThttps://github.com/sindresorhus/electron-store, https://www.electron.build
adm-zipMIThttps://github.com/cthackers/adm-zip
Inter, Outfit, Fira Code (fonts, via Fontsource)SIL Open Font License 1.1https://fontsource.org

Build tools (Vite, Tailwind CSS, TypeScript and so on) are not distributed with the application.

A mistake or an omission? Write to us: yanis.aksas@gmail.com.