Roman app icon

RomanJapanese input method (IME) for macOS — latest 1.18

Roman is a Japanese input method for macOS that brings an LLM (large language model) into kana-kanji conversion. Type romaji continuously and you get kanji-kana text that fits the context. Conversion, learning and inference all run on your own Mac.

Typing romaji continuously; the text turns into kanji-kana as soon as typing pauses
Type romaji continuously — conversion happens when your hands pause

No conversion key

keystrokes  nihongonyuuryokuhakawaru
             │
             │  while typing
             ▼
kana        にほんごにゅうりょくはかわる
             │
             │  when typing pauses
             ▼
converted   日本語入力は変わる

Roman is a form of live conversion — it follows your typing without a conversion key — but it does not commit text as you type. Instead it uses the pauses between keystrokes as the moment to convert. Candidates come from dictionaries, are judged by AI, and are combined with what Roman has learned from you.

Five characteristics

Conversion accuracy

Accuracy is measured on the public evaluation set AJIMEE-Bench (200 items built from the Japanese Wikipedia input-error dataset; 100 with a preceding sentence, 100 without). Acc@1 is how often the first candidate is already correct; CER is the character error rate.

First candidate correct (Acc@1) 80.5% (without context 83.0% / with context 78.0%)
Character error rate (CER) 2.60%
Version measured Roman 1.18 (2026-08-19; 1.17 was Acc@1 73.5% / CER 4.85%)

Method: each item goes through the same path as normal typing (dictionary, AI scoring, context-based re-selection), and the text that appears on screen is taken as the answer. For items with a preceding sentence, that sentence is passed as context. Any spelling the evaluation set accepts (okurigana or numeral variants) counts as correct. The figures are measured on the developer's Mac with its learned state; the conversion adapts further to your own vocabulary as you use it.

Download

Get the latest release (GitHub)

The package (pkg) is about 185 MB. On first install it downloads about 6.7 GB of language models (the installer asks before downloading). Expect 15–60 minutes depending on your connection.
Documentation is in Japanese: basic operations (with animations), installation guide and user manual.

Requirements

CPU Apple Silicon Mac (AI runs locally; Intel Macs are not supported)
Recommended: M4 or newer
Memory 16 GB or more (the conversion AI resides in memory, about 5 GB)
Recommended: 24 GB or more
Storage About 10 GB free (0.4 GB for the app, 6.7 GB for models and runtimes, plus working space)
OS macOS 14 or later

Privacy

Conversion, learning and AI inference all happen on your Mac. What you type is never sent to the internet.

Roman uses the network in only two situations:

  1. Downloading the language models during installation, from their official distribution sites (once only)
  2. The monthly check for a new version, if you turn it on (off by default)

Feedback

Bug reports, conversion-quality reports and feature requests are welcome on GitHub. For a conversion problem, please include the keystrokes you typed and the text you expected.

Report an issue | Discussions