ScreenKit

Windows desktop tool (ScreenKit.exe, window title ScreenKit): screenshot recognition, annotation, recording, speech, translation, a dictionary, and face, plus file transfer and screencast with the Android companion. This PC also has an HTTP API and a browser tools page.

Current version: 1.0.28 · Releases · Changelog · 中文

Screenshot and recognition

• Screenshot OCR: A hotkey or the menu selects a region and recognizes text and barcodes; the recognition engine can be switched, and recognition can overlay a translation.
• Screenshot annotate: Rectangle, ellipse, arrow, pen, and text; on finish it copies as an image, a file, or a path.
• Repeat last capture: A hotkey or the menu grabs the last region you selected again.
• Long screenshot: Click a scrollable window and it scrolls and stitches one long picture.
• Screenshot history: Browse saved pictures as thumbnails and pan, zoom, annotate, or copy them. Pictures older than the retention period are deleted in the background at startup and every 24 hours after that.
• Overlay text: Draws the recognized text over the picture to select from.
• Clipboard: Paste a picture and recognize, annotate, or save it. The tray's Copy clipboard image as file drops the picture into the screenshot folder so Explorer can paste it; a picture already in that folder is copied as is, without saving another copy.
• PDF workbench: Open a PDF, recognize it page by page, edit the text, and export a searchable PDF.

Recording

Capture → Screen record or GIF record: click a window, or drag a region.

• The red frame is drawn outside the selection; size and aspect can be set before start, and the control bar can be dragged and collapsed. The audio source can be changed while recording, and the bar shows each recorded channel as a small live meter instead of source text.
• Region recording: Writes an MP4, with system audio, the microphone, or both, and optional mouse and click highlights.
• GIF record: Uses the same region capture and writes a silent GIF, with a frame rate and a palette.
• Record options: The frame rate and the same shorter-side cap as screenshots. Pick the microphone here, with a system-default entry, and watch small vertical level bars for the microphone and the system sound.

Speech, translation, dictionary, and face

• Speech recognition: Live captions with an offline or streaming model.
• Speech synthesis: Windows speech, SAPI, offline speech, Edge natural voices online, and voices in the local Chrome. Chrome lists only installed languages. Chrome model installation opens Chrome with this app's private profile on the model page. An installed voice can play a short test line. Settings → Speech synthesis is a per-language table of engine, voice, and rate. Chinese, Japanese, Korean, and English always stay; other languages can be added or removed. Dictionary entry speech, and Read aloud in the selection popup when the engine is Auto, use that row.
• Voice input: The hotkey starts and finishes it, and the result goes to the current input position.
• Chat: Uses a configured LLM, with bubbles, microphone input, and speaking.
• LLM log: The latest ~1,000 requests with the model, elapsed time, and the request and response.
• Translation: Local ONNX, a configured LLM, or the local Chrome. Auto mode translates between the native and learning languages and shows the detected direction; the tab and popup pick the engine and model. Chrome language lists show only installed packs, and Chrome model installation opens the same private profile on the model page.
• Face: Detection and comparison, with optional landmarks and gender and age.
• Chinese to pinyin: Full spelling without tone marks, or one lowercase initial per character.
• Wubi, Japanese, and Korean IME: Type with a candidate bar in this app and in other programs. Japanese candidates include the dictionary kanji spellings, plus verb and i-adjective conjugations. A partial reading also lists every word that can still be completed. An old lexicon file is marked as a new version under Help → Install features, where it can be reinstalled or removed. Turn it on from Tools, switch languages from the tray; set hotkeys, enable languages and manage the lexicon in Settings → Input method (disabled languages are skipped by the cycle hotkey).
• Simplified/Traditional: Simplified on top, traditional below, following Taiwan character forms.
• Japanese yomi: Turns a Japanese sentence into readings, by word or by character.
• Calendars: Gregorian to lunar (sexagenary cycle and leap months), plus Japanese, Taiwan, Hebrew, Hijri, Persian, and others.

Dictionary

The main window, or Tools → Dictionary. Look up Chinese, English, Japanese, and Korean.

• Language filter: All, Chinese, Japanese, Korean, English.
• Pure Latin input is romanized for Japanese and Korean search (romaji to hiragana, Korean romanization to Hangul), such as watashi and hanguk.
• ? is a wildcard for one or more characters, such as col?r for color and colour, or w?rd for ward and word.
• A hit has pronunciation, part of speech, senses, phrases, and examples, all of which can be spoken; Export writes every hit of this search. A verb, adjective, or noun also has a forms tab. An English verb can take one or two objects, chosen from the part of speech by default, or typed in.
• Double-click, drag, or right-click inside an entry to pop up the lookup window, up to 100 hits. Dictionary entries always do this.
• Settings → Dictionary sets how many hits to list, how long to keep the database open, and the selection popup.
• The dictionary hotkey is empty by default: it brings the window forward on the dictionary when it is not the main window, and hides the main window when it is.
• The web dictionary is its own page at /dict, opened from a card under Text on the tools page; Ctrl+click opens it in a new window. It has the same search, four languages, speech, and export.
• Selection popup is off by default and can be turned on on the dictionary page, under Settings → Dictionary, or on the tray. While it is on, dragging or double-clicking text in this program or another shows a lookup popup that does not take focus. With no hits the window stays the same size as when it has hits. A selection with punctuation a word cannot contain, or longer than a word, opens the popup without querying the dictionary. Translate on the right defaults both languages to Auto: native text goes to the learning language, anything else goes to the native language. After a manual language change, click Translate once. The source text can be edited, and the resolved source and target languages are shown beside it. Switching dictionary language or translating does not change the popup width. Drag the lower-right corner to resize, or drag an empty area to move it. The size is saved when you quit and restored next time. Read aloud speaks the text sentence by sentence and highlights the sentence being spoken, with a choice of engine (including Chrome), speed, language, and voice. Auto uses that language's engine, voice, and rate from Settings → Speech synthesis. While that tab stays open the popup does not dismiss itself and ignores new selections.

Files and screencast

File sync

On the PC, open File sync; the phone and the PC are on the same LAN.

• Dropping files onto the list puts them in the inbox; dropping onto the lower area sends them to the phone while it is connected, and a phone share or upload writes to sendfile/.
• Web manager uses the same port: the PC opens /files and the phone /m, where a login allows uploads, folders, rename, and delete.

Screencast

This program receives while it is running, and that can be turned off in Settings; Tray → Tools → Screencast opens the screencast page. Use the same Wi-Fi, with guest isolation off.

• PC to PC: Pick a saved PC, scan the LAN, or type an IP; the picture is kept within 1000×1000 by default.
• Phone to PC: Pick a saved PC or scan the LAN in the phone app, over the LAN or a USB cable (debugging or accessory).
• The viewer is not pinned on top, the picture can fit the window or fill it, closing it disconnects, and quality and the audio source can be changed while casting.

Tools

• Tools page: The main window's Tools tab lists the desktop windows and the web tools by category. The left side picks a category, including Favorites and All; the right side shows cards with an icon and a label, a search box, a click to open, and a star to favorite a card. All groups the cards under a heading for each category. The tray shows Favorites beside Tools and before it, only when something is favorited, in the same order.

• Image convert: Batch convert to JPG, PNG, palette PNG, or BMP, with a shorter-side cap, rotation, and mirror.

• Batch video convert: Batch convert to MP4, MKV, or WebM, with a shorter-side cap and the audio kept. Optional hardware acceleration (NVENC / QSV) falls back to the CPU; the list shows each file's progress and the status bar shows CPU / GPU usage.

• Video to GIF: Pick a start and an end and write a silent GIF, with a frame rate and a palette.

• Character art: The Mode list picks Shades ASCII, Dot shading, or one of the line drawings; full-color character art is drawn in a console window.

• Pixel art: Choose a width and a height, paint on large cells, and preview at real pixel size. Copy or save a PNG.

• Character bitmaps: Draw each character as a dot matrix and export a C array, hex, or dot-matrix text.

• QR / barcode: Generate QR, Data Matrix, Code 128/39, EAN, and UPC.

• Batch rename: Edit target names by hand or with rules such as %1 and #, and sort by name or date.

• Fast copy: Copy, cut, delete to the Recycle Bin, or make a symbolic or hard link, and register an Explorer cascade menu. Counting the source list and starting a transfer each open a progress window that updates the file count, total size, copied count, and copied size, and can be cancelled. Count files reports just the file count and size.

• Hash: MD5, SHA-1, and SHA-256. Paste an expected value to compare.

• Text tools: Base64, URL, hex, escapes, case, whitespace, counts, JSON pretty-print, and more.

• Document reader: Open or drop Markdown, Word (.docx/.doc), PDF, Excel (.xlsx/.xls), CSV, images and text or code files — several at once — and each opens as a tab in a self-drawn title bar. A tab is parsed only when you switch to it. Zoom, page through, search, and click images to view them full size; Markdown also exports to Word (needs Word installed) or PDF (printed by Edge/Chrome). Recent files lists the last ten, and the tabs that were open when you closed the window come back next time; drag a tab to reorder, drag it out into its own window, or drag it back to merge. The Word/Excel parsers install from Install features → Tools → Document reader and are not part of the download.

• Word/PDF to MD: Convert a .docx or a text PDF to Markdown, then preview, copy, or save it. Images are extracted into the chosen folder (default images/001.png; {name} becomes the document name), and PDF text comes from the installed PDFium; scanned pages need PDF recognition first.

• Password generator: Generate passwords from a length and character classes, or hand a sentence to a configured LLM and spell the translation out.

• Network: Diagnostics, IP scan, and port scan, covering Ping, DNS, Wake-on-LAN, trace route, and more.

• Ports in use: Lists the TCP and UDP ports in use and the process behind each, and can open that folder.

• Network monitor: Lists connections per process with send/receive bytes and rates, and a packet capture tab that parses protocols, shows a connection's packets, reassembles HTTP streams, and imports or exports pcapng. Capture needs Npcap and admin rights, so it offers to reopen itself elevated.

• USB capture: From the network tools, captures USB transfers. A device tree on the left lists what is connected; pick one device to capture only it, pick a hub to include everything under it, or pick nothing to capture all. The list shows control, bulk, interrupt and isochronous traffic by device address and endpoint, with protocol fields and a hex view. Imports and exports pcapng that Wireshark can open. Needs USBPcap and admin rights, and offers to reopen itself elevated.

• TLS certificate check: Enter host:port to connect once and see the TLS version, cipher suite, and full chain with validity, SAN, and thumbprint; copy it as PEM.

• FTP file manager: Connect over FTP, FTPS, or SFTP with a server-only file list: drag files or folders from Explorer into the list to upload, drag files out of the list to hand them to Explorer for download, or use Download to… for the selected files or a whole folder. The transfer queue below shows progress, speed, and bytes done, and supports parallel jobs with pause and resume. Sites and passwords can be saved. TFTP is available as a protocol too: type a file name to download it, or drop a file in to upload it under its own name. TFTP cannot list directories, so the list is replaced by a name-based panel, and it needs no extra libraries. The libraries install on demand from Features → Tools.

• FTP server: Turn this computer into a file server from the FTP server page. Pick a root folder (ftproot next to the program by default), a port, and one user name and password; leave the user name empty to allow anonymous access. The same page can also run TFTP on its own UDP port over the same folder, and the two can be started and stopped independently. Once started the status bar shows the listening ports and the page logs each connection and transfer on its own line. Both are off by default.

• System info: System, USB, serial ports, printers, sound, fonts, displays, cameras, Bluetooth, disks, and other devices. The system page also covers BIOS, chassis, install date, system language and time zone, memory slots, GPU driver, shared folders, local users, and logon sessions; disks list their partitions, network adapters show DHCP and the subnet mask, and the USB page adds controllers and hubs. On the USB devices page, select a device and click Read descriptors to see its device and configuration descriptors, interfaces, endpoints, strings, and HID report layout (read-only).

• System tools: Read-only lists of processes, environment variables, startup items, installed programs, services, hotfixes, and Store apps, plus file locks and file associations.

• Performance: A borderless window with CPU, GPU, memory, network, and disk, with a pin and an update interval.

• File info: Reads the header type and shows version, image, media, and text-encoding details. EXE and DLL files get another page for sections, imports, exports, the signature, and public .NET types.

• Code stats: Drop several folders or files and see files, lines, code, comments, and blanks per language. Click a language to list its files by line count. It can follow .gitignore and extra ignore rules.

• HTTP request debugger: Requests are saved in groups; parameters are one key=value per line, headers are one name: value per line, and a POST can be JSON, XML, or raw text. The URL and parameters stay in sync, a Chrome User-Agent and the Content-Type are filled in automatically, and a group can be exported to JSON and imported back.

• MQTT debugger: The client connects to any MQTT broker to subscribe and publish, with + and # wildcards, QoS, retained messages, and hex send; the server tab runs a broker on this PC for other devices to connect to.

• TCP/UDP/serial debugger: Open it from Network tools and pick the protocol at the top. UDP listens and sends; TCP connects or listens, then sends; serial picks a port, baud, data bits, parity, and stop bits, then opens and sends. Datagrams go as hex or in the selected encoding, can repeat on a timer, and can auto-reply with the current input. The last protocol, address, port, serial settings, and payload come back next time.

• SOAP debugger: Read a WSDL from a URL or a local file, edit parameters from its XSD, preview the envelope, and call SOAP 1.1/1.2 operations. It can also run a local mock service with per-operation responses, request logs, and importable/exportable config.

• MIDI synthesizer: Play with the mouse or the keyboard, open, change, and save MIDI files, and see a live waveform.

• Sound recorder: Record a microphone, system sound, or both, then play it or save a WAV. Level blocks show the current input device and the system sound in real time, even before recording starts.

• Camera: Preview a camera, take photos and videos, and scan QR codes and barcodes. Double-click the picture for fullscreen; double-click again or press Esc to leave it.

• Scientific calculator: A borderless keypad calculator with trigonometry, logarithms, powers, roots, factorial, and memory.

• Desktop note: A borderless translucent note for text or a to-do list; content and position are remembered. The pin in the title bar keeps it above other windows, and that too is remembered.

• RTSP test server: Encodes a bouncing picture to H.264 and serves an RTSP address on the chosen port.

• Auto key: Sends keys or clicks in a row to the foreground window; the default F6 starts and stops it while the window is open.

• Database query: Drop a SQLite file in to open it, or connect to SQL Server, MySQL or Oracle (the last two drivers install on demand from Install features). The left side lists tables and views; double-click one for its rows, click Schema for columns and the CREATE statement, or run any SQL with F5 or Ctrl+Enter. Save the connections you use often and pick one to fill in the settings.

• Window manager: Lists top-level windows (hidden ones too, if you like) and frames the target you pick. Shows the window tree plus HWND, class, process, rect, and style bits; edits the title and rect, pins, shows or hides, enables or disables, sends custom messages, and repeats mouse clicks at client-area coordinates.

Web tools

• Text
  • Text convert: Encoding, escaping, and common text transforms
  • Chinese to pinyin: Characters to pinyin or initials
  • Document reader: Preview Markdown, Word, PDF, Excel, CSV, images and text files as tabs rendered on demand, with click-to-zoom images
  • Novel reader: A separate page (/reader) like the dictionary, opened from a card under Text on the tools page; Ctrl+click opens it in a new window. Drop or add txt/md files; they stay in this browser. Select text for the dictionary popup (drag its edges or corners to resize, or maximize it). It reads with the current browser’s own voices by default, and can switch to Chrome offline or other voices. Reading starts at the top of the screen or at the selected word and highlights the current sentence. Google voices do not speak online; a missing offline pack is installed when reading starts, with a progress dialog that can be cancelled, and each voice shows whether that pack is installed. Choosing browser voices shows an Install models link
  • Chinese segmentation: Split by word, sentence, or grapheme
  • In-browser model: Run text tasks on the browser’s local model; Speak can filter voices by language. Google voices use the installed offline pack, and the list shows whether that pack is installed. The page link opens the Chrome model page
  • Translate: Translate text into another language, with its own engine and local ONNX model pickers
  • Password generator: Generate passwords and remember the last length, count and character options
  • Regular expressions: Find regex matches
  • Number names: Write a number in several readings, and see the common floating-point formats too
  • Test data: Generate fake data by type
• Math
  • Scientific calculator: Scientific calculation
  • Radix conversion: Convert among base 2, 8, 10, and 16
  • Byte decoder: Type hex bytes (auto-grouped as XX XX, Backspace removes a byte) and read them as int8 through fp64, fp8/fp16/bf16, ASCII, and UTF-8, with a choice of byte order and a grouped list by type; floats also show their m × 2^e form
  • Unit conversion: Length, weight, currency, and more
  • Random number: A number inside a chosen range
  • Function graph: Plot 2D curves, 3D surfaces, and implicit equations such as x^2+y^2+z^2=9 for a sphere, with built-in examples
  • BMI: Body mass index from height and weight
  • Mortgage: Equal payment or equal principal
  • Compound interest: Interest compounded yearly
• Speech
  • Speech: Read text aloud
  • Speech recognition: Turn speech into text
  • 8-bit synthesizer: Square-wave tones and effects, octave -/+ buttons (C1-C7), and a live waveform
• Calendar
  • Calendars: Gregorian alongside lunar and other calendars
  • Timestamp: Unix time and local time
  • Date arithmetic: Difference or offset between dates
  • Timer: Stopwatch and countdown
  • World clock: Local time in other places
  • Workdays: Move a date by workdays
• Image
  • Text recognition: Read text in a picture
  • QR / barcode: Make a QR code or barcode
  • Scan QR / barcode: Read a code from a picture
  • Camera: Take a photo or scan a code. Double-click the picture for fullscreen.
  • RTSP player: Play an RTSP video
  • Image Base64: Picture and Base64
  • Image to ICO: Turn a picture into an icon
  • Color picker: Pick or sample a color
  • CSS gradient: Preview a CSS gradient
  • Drawing board: Draw on the page
  • HTML preview: Write HTML and see it
  • Placeholder image: Make a placeholder picture
  • Random colors: A set of random colors
• Lookup
  • Japanese conjugation: Enter the dictionary form or pick a word from the dropdown; auto tells a verb from an i-adjective, na-adjective or noun, and the type can be set by hand. Verbs are listed by class with auxiliaries, politeness, dialect forms and N5-N1 patterns; adjectives and nouns get their own patterns and literary forms, and rough, written, character-speech and sentence-ending groups are listed separately. Each form has a speak button.
  • Korean word forms: Pick verb, adjective or noun, type a word or choose one from the list. Forms are grouped by speech level, grammar pattern, contraction, colloquial and literary ending, classical ending, character speech, in-group slang, rough endings, dialect, North Korean, DPRK broadcast or Yanbian. Each form has a speak button.
  • Russian word forms: Pick a type and enter the base form; every form is listed at once. Verbs show tense, mood, participles and gerunds, adjectives and nouns their full declension, each form with a speak button.
  • English word forms: Pick auto, verb, adjective or noun and type a word or choose one from the list. Verbs list the sixteen tenses with negatives, questions, passive and moods. Objects follow the dictionary by default: none if intransitive, one if transitive, two if ditransitive, and the choice can be set by hand. Each object can be picked from the list or typed. Adjectives list the comparison forms, nouns the plurals, articles and agreement, each with a speak button.
  • Word-form export: --conj-json [ja|ko|en] exports the full table by type; Russian uses node scripts/export-ru-conj.js.
  • Color chart: Named colors
  • HTTP status codes: Status codes, descriptions, and specs by 1xx–5xx, plus common non-standard ones
  • MIME types: MIME types, file extensions, and Content-Type examples
  • Common ports: TCP/UDP ports, services, and what they are used for
  • File signatures: Identify the real format from a file's hex header
  • Time zones: IANA zones, abbreviations, and standard/DST offsets
  • Country, language & currency codes: ISO codes for countries, languages, and currencies
  • Japanese name readings: Look up how a surname or given name is read, in both directions: kanji to kana, or kana back to kanji. A full name is split into one surname and one given name, and Random can fill in a generated name. 97k surnames and 122k given names, browse by kana row, list every reading of a name in a vertical stack, and play each one; the data is downloaded on first use instead of shipping with the app
  • English irregular verbs: Base, past, and past participle; search by any form or meaning, and filter by AAA, ABB, and other patterns
  • Key codes: A key's event.code, event.key, keyCode, and Windows VK
  • Linux commands: Commands by file, package, process, network, and more, each shown right in the list with a commented multi-line example, plus Bash syntax help, context lines, and multi-line matching; switch between Ubuntu, Debian, Deepin/UOS, RHEL, Fedora, openEuler, Arch, openSUSE, and Alpine, and the last choice is remembered
  • Windows commands: Windows PowerShell, pwsh, and CMD commands by category, each shown right in the list with a commented multi-line example, plus a syntax-help group for all three shells; the last shell is remembered
  • SQL functions: Look up functions and syntax for MySQL, SQL Server, Oracle, SQLite, and PostgreSQL, grouped by strings, numbers, dates, casts, aggregation, window functions, JSON, and metadata; the last database is remembered
  • Linux software: Open-source Linux packages and install commands for common apps
  • This browser: What the browser can read about this device
  • USB IDs: USB vendor and product
  • Emoji lookup: Emoji by Unicode category, searchable in Chinese and English by keyword or code point, click to copy
  • Unicode chart: Unicode characters; symbols such as arrows, math, shapes, hexagrams, mahjong and playing cards come with Chinese and English names in the details, and can be searched by name
  • ASCII chart: ASCII characters
  • GBK chart: GBK characters
  • Morse code: Morse code
• Talk
  • Chat room: Send text, pictures, and files
• Files
  • File transfer: Move files between the phone and this PC on the same LAN

Hotkeys

They can be changed in Settings. An empty hotkey string turns that hotkey off.

Hotkey	Action
Ctrl+Alt+O	Show or hide the main window
Ctrl+Alt+Q	Screenshot annotate
Ctrl+Alt+G	Repeat last capture region
Ctrl+Alt+W	Screenshot and recognize
Ctrl+Alt+V	Voice input; press again to finish
Ctrl+Alt+B	Live captions
Ctrl+Alt+T	Show or hide the translate popup
Ctrl+Alt+P	Cycle the screenshot copy mode: image, file, path
Ctrl+Alt+H	Open the web tools home in the browser

Install, language, and updates

The slim package does not include models or the large runtimes; 7za.dll is bundled to extract 7z archives. Screenshot, annotation, recording, Windows OCR, system speech, most tools, file transfer, and the PC side of screencast work right after install; Windows OCR and system speech also need that language in the operating system.

Barcode, ONNX text recognition, offline speech, face, local Chinese–English translation, the dictionary, the input method, PDF, FFmpeg, CUDA, and DirectML are installed or removed under Help → Install features, and using a component that is not installed yet shows a prompt.

Settings → General can turn a group of features off. The UI language is switched on the menu bar or on that same page: Chinese, English, Japanese, Korean, German, Spanish, French, Portuguese, and Russian. Help holds Check for updates, Diagnostics, and Memory. A newer version lists the notes for each release since the one you have; pick a version to read that one, or read them all.

Run

Windows 10/11 (x64). It needs .NET Framework 4.8.

The local HTTP port defaults to 1224; after Allow LAN access is checked, the same LAN can connect. File transfer, the web tools, and screencast share this port, and POST /api/ocr matches Umi-OCR text recognition. If that port cannot be opened, or the HTTP switch is off, a random port that accepts only this computer still serves the tools pages and the HTTP API, and menus and buttons open that port.

License

Application source in this repository is under the MIT License. The full text is LICENSE. Copyright (c) 2026 ScreenKit Contributors. Under the MIT terms you may use, copy, modify, merge, publish, distribute, sublicense, and sell it. The software is provided “as is”, with no warranty, express or implied.

The items below do not automatically use this repository’s MIT license. Each license is in THIRD_PARTY_NOTICES.md.

• ONNX Runtime, PDFsharp, PDFtoImage, NAudio, SharpCompress, Vortice, and Bogus are MIT. PDFtoImage also brings the Pdfium and Skia native libraries.
• OpenCV (OpenCvSharp) and ZXing are Apache-2.0.
• 7za.dll (7-Zip) is LGPL-2.1 or later. The license text is License.7za.txt next to the program.
• FFmpeg: the binding code is LGPL-3.0. The ffmpeg64 build itself is GPL or LGPL, depending on that build. Redistribution has to follow those terms.
• DirectML and CUDA / cuDNN follow Microsoft’s and NVIDIA’s redistribution terms.
• ONNX models such as text recognition are usually Apache-2.0, or the terms of that model pack’s author.
• NPinyin turns Chinese into pinyin. The package ships with no license file.
• SQLite (e_sqlite3.dll) opens the input-method database. It is in the public domain.

dict3.bin keeps Chinese, Japanese, Korean, and English in one file. Install features downloads and extracts it. Inside it:

• Chinese. Characters, words, and idioms come from mapull/chinese-dictionary (a pinyin dictionary). The license is MIT. The upstream notes say the origin of some material is unclear.
• Japanese. Word senses come from JMdict/EDICT (EDRDG). The license is CC BY-SA 4.0. Redistribution has to keep the EDRDG attribution and follow that project’s update terms.
• Korean. A derivative of the National Institute of Korean Language dictionary. The license is CC BY-SA 2.0 KR.

Step-by-step use, the API, and the build are in the full guide. The phone app is in android/README.md.