Read any Japanese, however it reaches you
A line in a video that catches you out. A sign at the station. A page from a manga. Get it into the app, and see it broken down word by word.
However the Japanese reaches you
Most of the time you've already got the text. Sometimes you've only got audio. Sometimes you've only got a photograph. The app handles all four, and the result is the same however it got there: a full breakdown you can study.
Paste
Anything from your clipboard, instantly.
Type
If your hands are already on the keyboard.
Microphone
Record it and let the app transcribe.
Camera
Point and shoot, on iOS.
The camera lives on iOS, where unprepared reading actually happens
Signs at the station. A page from a book. A t-shirt slogan. A menu. Point, shoot, and the text comes through ready to break down.
On macOS the same text is almost always already digital, so paste does the job.
From spoken Japanese to broken-down sentence
Tap the microphone, record what you heard, tap to stop. The app transcribes locally, so your audio doesn't leave the device.
If the transcription isn't quite right, edit it before sending it off to translate. Mishearings happen, yours and the app's.
The full breakdown is saved on your device.
A working surface, not a finished answer
The breakdown shows you every word in the sentence, colour-matched between Japanese and English, with the reading and dictionary form attached. Tap any word to open its dictionary entry. Tap any kanji to pull it apart into components.
If a word's mapping isn't quite right, or you'd just phrase it differently without losing the meaning, edit it. The breakdown is yours.
Polished where it matters
Readings on every word, on your device
Once you've installed the furigana dictionary, every breakdown gets readings without a network round-trip. No waiting for a server, no surprise gaps when you're offline.
Hear any line spoken
Every translation has playback. Use the offline voice the app comes with, or connect a higher-quality voice from your provider.
Everything you've translated, kept
Every translation is saved on your device with its breakdown, audio, and source. Search the list, copy a line on long-press, come back to anything later. Nothing gets sent anywhere, they're yours.
Bring your own translation provider; switch whenever you want.
Bring your own
Translation runs against a cloud model. Local models aren't quite small enough and accurate enough for learning yet. Use OpenAI, Google, or any OpenAI-compatible endpoint. Keys are stored on-device and used only for API requests. The costs are yours, and the only data sent over the network is the text you're translating.
Everything else stays local: your dictionary, your saved translations, your transcripts, your recordings.
Quick answers
Common questions
Does my audio leave my device?
No. Microphone recordings are transcribed locally on your device. Only the resulting text is sent to your translation provider.
Is camera translation on macOS?
No. Camera input is on iOS. On macOS the text is usually already digital, and pasting it in is the simpler path.
Can I use it offline?
Translation itself needs the network, since it runs against a cloud model. The dictionary, your saved translations, transcription, and furigana all work offline.
Which providers can I use?
OpenAI, Google, and any OpenAI-compatible endpoint. Your keys are stored on your device and only used to make requests to your provider.
Coming soon to iOS and macOS. Up next: the dictionary.