Skip to main content

Apps

Four free apps share one on-device engine

Live Linguist is coming to the Mac, iPhone and iPad, Android, and PC. Each build runs the same 29-language simplifier on your device, needs no account, and keeps audio local. The macOS app is available now as a direct download. The store releases are pending.

Store release status

The iOS/iPadOS, Android, and Windows builds are pending official store release. No public store link exists yet. Links will appear on this page when each release goes live. You can download the signed, notarized macOS build now.

The lineup

The same tool, wherever the conversation happens

The apps share the model family, the easy-language registers, and the on-device pipeline. Platform integration differs by microphone permissions, speech recognition, and each store’s distribution rules.

macOS

Available now

Direct download available now · Mac App Store build pending

The reference build shows live captions and the verbatim transcript, then writes each segment in easy language on Apple silicon.

  • Apple silicon (M-series) Mac
  • macOS 14.4 or later
  • Version 1.1.28 · ~11 MB .dmg
  • Signed and notarized; hosted on Cloudflare
Download the macOS app

The download needs no GitHub account.

iPhone & iPad

Pending release

App Store release pending

The same simplifier in a pocket-sized app for on-device speech and easy-language captions.

  • On-device speech recognition and simplification
  • Runs on an A18 Pro (8 GB) in our tests
  • Needs no account and keeps audio on the device
  • The store listing will publish platform requirements

App Store link forthcoming.

Android

Pending release

Google Play release pending

The Android build processes speech on the device and simplifies it in the same language. It needs no account.

  • On-device pipeline
  • All 29 easy-language registers
  • Needs no account and keeps audio on the device
  • The store listing will publish device requirements

Google Play link forthcoming.

Windows PC

Pending release

Microsoft Store release pending

A desktop build for Windows with the same live transcript and easy-language output as the Mac app.

  • On-device pipeline
  • All 29 easy-language registers
  • Needs no account and keeps audio on the device
  • The store listing will publish system requirements

Microsoft Store link forthcoming.

Shared by every app

Private by default, free to use

On-device by design

Audio capture, speech recognition, and simplification run on your device. The app sends no audio to a server and needs no account.

Keeps the target language

German becomes simpler German; French becomes FALC; Japanese becomes Yasashii Nihongo. The learner stays inside the language they are acquiring.

29 registers, two model sizes

The 0.6B model is the live-caption driver. The 1.7B model is the quality option. Both are 4-bit and sized for edge devices.

Free of charge

The apps cost nothing. Aquilops LLC owns the closed-source apps and funds the project as an educational effort. The models and dataset remain open source.

Before the store releases

Use the Mac build, or take the models anywhere

The macOS download is live today. If you are building for another platform, the same 0.6B and 1.7B easy-language models are on Hugging Face with the full evaluation tables, so you can reproduce the pipeline on your own hardware.

Shape the next release

Tell us what your classroom or office needs

We want to hear from language educators, interpreters, accessibility teams, and public-sector officials about the language pairs, registers, and workflows that matter to you. Send links to what you build with the open models or dataset.

Use, citation & ownership

Free for education, with citation samples and clear ownership

Dylan Goldblatt created Live Linguist’s free software, open-source datasets, and open-source models for educational purposes. They support language learners, educators, accessibility teams, and researchers. They do not replace a certified accessibility service, a medical device, or human easy-language review.

If you use the project in teaching, research, or a published build, attribute Dylan Goldblatt. The samples below cover the usual style guides; update the version and year when you cite a later release. For the models and dataset, cite the Hugging Face repository you used.

APA 7

Goldblatt, D. (2026). Live Linguist: On-device easy-language caption simplification (Version 3) [Computer software]. https://ndgold.com/live-linguist/

MLA 9

Goldblatt, Dylan. Live Linguist: On-Device Easy-Language Caption Simplification. Version 3, ndgold.com, 2026, ndgold.com/live-linguist/.

Chicago 17

Goldblatt, Dylan. Live Linguist: On-Device Easy-Language Caption Simplification. Version 3. Computer software. 2026. https://ndgold.com/live-linguist/.

IEEE

D. Goldblatt, "Live Linguist: On-device easy-language caption simplification," Version 3, 2026. [Online]. Available: https://ndgold.com/live-linguist/

BibTeX: project

@software{goldblatt2026livelinguist,
  author  = {Goldblatt, Dylan},
  title   = {Live Linguist: On-Device Easy-Language Caption Simplification},
  year    = {2026},
  version = {3},
  url     = {https://ndgold.com/live-linguist/},
  note    = {Open models and datasets for 29 easy-language locales}
}

BibTeX: quality model

@misc{goldblatt2026easylanguage,
  author    = {Goldblatt, Dylan},
  title     = {Qwen3-1.7B-EasyLanguage-4bit},
  year      = {2026},
  publisher = {Hugging Face},
  url       = {https://huggingface.co/ndgold/Qwen3-1.7B-EasyLanguage-4bit}
}

Ownership

Aquilops LLC holds the sole intellectual property in the closed-source applications. They cost nothing, and their source stays closed. © 2026 Aquilops LLC. All rights reserved.

The open models and datasets carry their own licenses: Apache-2.0 for the models, CC BY-SA 4.0 for the dataset. The Qwen3 base model and German4All source data keep their upstream licenses. Aquilops LLC owns the closed-source application, its name, and its icon.