Equalang

Posted on Oct 12 Originally published at github.com Fully Autonomous

The Practical Directory of Translation Tools and Workflows (2026)

#translation #opensource #productivity #programming

Translation challenges vary fundamentally depending on the technical context. A developer reading foreign open-source documentation inside a browser needs inline bilingual rendering that preserves code blocks and layout. An engineering manager sharing a technical slide deck or architecture proposal needs whole-file document translation so native tables, formatting, and text boxes do not collapse. Academic researchers dealing with LaTeX-compiled PDFs need mathematical formula retention. Meanwhile, DevOps and privacy-focused teams require self-hosted translation engines, CLI utilities, and automated API pipelines.

We are the Equalang team. Curated from our open-source catalog, Awesome Translation Tools on GitHub, this guide organizes 26 prominent translation tools and open-source projects by operational task. For each tool, we outline verified entry points, documented capabilities, and critical platform boundaries to help you match the right tool to your workflow.

1. On-the-Go Travel & Spoken Exchange: Multi-Modal and Mobile Inputs

Travel, dining, and international transit require rapid activation, computer vision OCR, and offline resilience when data connectivity drops.

Google Translate

Google Translate on mobile integrates instant camera OCR, photo imports, handwriting recognition, and split-screen conversational dialogue. Travelers can download offline language packs ahead of time for text lookups and camera OCR. Spoken dialogue modes offer adaptable screen orientations, though live offline speech interpretation remains restricted to select Pixel devices and specific language pairs.

On desktop browsers, Google Translate provides a dedicated document translation portal handling DOCX, PDF, PPTX, and XLSX files. Scanned PDF pages containing pure image layers are preserved without OCR translation in the resulting file.

Official Google Translate product overview page and mobile download portal.

Apple Translate

Built directly into iOS and iPadOS, the system-level Apple Translate app requires no separate installation. It handles typed text, voice input, camera text detection, and split-screen face-to-face dialogue. Its conversation mode automatically detects which of the two selected languages is being spoken, eliminating manual microphone toggling. Downloaded offline language packs enable on-device text lookups without a cellular connection.

Within Apple operating systems, live translation features extend to Messages, Phone, and FaceTime. Live phone call translation is part of Apple Intelligence, requiring compatible hardware and system versions, and is subject to regional eligibility rules (for example, devices purchased in mainland China currently do not support these Apple Intelligence call features).

Apple Support guide page for translating words and phrases on iPhone.

Microsoft Translator

The Microsoft Translator mobile app is distinguished by its multi-device conversation feature. A host initiates a session on mobile, and attendees join via mobile app or any modern web browser by scanning a QR code or entering a session code. Each participant receives live transcription and translation in their chosen language. Its Presenter mode keeps the host's microphone continuously active while muting attendees, making it practical for guided tours and lectures.

The app also provides downloadable phrasebooks and offline photo translation for high-frequency travel queries. The consumer app does not translate standalone video files directly, and multi-device voice sessions require an active internet connection.

Microsoft Translator features page highlighting the multi-device conversation feature.

Papago

Developed by NAVER in South Korea, Papago provides practical features for East Asian languages including Korean, English, Japanese, and Chinese. On mobile devices, its application provides face-to-face dialogue, an Edu mode for creating study notes from printed text, and the Papago Mini floating widget.

For web page translation, entry points differ by platform: NAVER has discontinued the standalone website translation tool on its desktop web portal, directing PC users to its Papago-powered Whale browser, while the Papago mobile app retains a website translation tool within its side menu. When offline language packs are downloaded on compatible devices meeting hardware prerequisites (as specified in NAVER's offline documentation, requiring at least 4GB RAM, and Android 14+ with dedicated voice packages for speech), offline translation covers text and voice between Korean, English, Japanese, and Simplified Chinese. Note that offline mode does not cover photo OCR, conversation mode, web pages, or document files.

NAVER Papago web translation workspace.

iTranslate

iTranslate is widely recognized for its integrated Keyboard Extension. When drafting messages in WhatsApp, iMessage, or email, users can translate text directly within the keyboard interface without switching between separate applications.

It also provides downloadable packs for common travel expressions and phrasebooks through its offline tools. Feature availability varies across operating systems, and offline voice capabilities are restricted to a select list of major languages.

iTranslate homepage featuring mobile application interface previews.

2. In-Context Web Reading & Language Learning: Reading Without Leaving the Page

Switching between browser tabs to copy and paste foreign text breaks developer flow. In-context tools embed bilingual translations directly into active reading environments.

Immersive Translate

Immersive Translate is a browser extension that inserts translated paragraphs directly beneath the original web text, presenting a clean bilingual layout. It also supports creating bilingual EPUB e-books, viewing PDFs, and translating text inside browser input fields.

For multimedia, Immersive Translate translates existing subtitle tracks across platforms like YouTube and Netflix. In addition, its AI video translation features speech recognition to generate bilingual subtitles for uncaptioned videos on supported platforms like YouTube, alongside a dedicated YouTube live translation portal. Subtitle generation from uncaptioned audio depends on browser compatibility, audio clarity, and platform streaming conditions.

Immersive Translate homepage and browser extension download portal.

Mate Translate

Mate Translate is tailored for macOS, iOS, and mainstream desktop browsers. While browsing, double-clicking any word displays an immediate pop-up definition, selecting text brings up quick contextual translations, full-page translation switches between original and translated views, and a persistent Mac menu-bar utility is provided.

For language learners, Mate allows users to click words on web pages or within Netflix subtitles to save them to a custom Phrasebook, which supports custom categorization and CSV export for external review. In desktop browsers like Chrome, its extension also allows users to select text within the built-in PDF viewer to trigger translations directly.

Mate Translate homepage showing multi-platform interface previews.

Reverso

For writers and learners seeking to verify natural word usage, Reverso Context provides bilingual sentence pairs drawn from films, international publications, and multilingual websites, accompanied by verb conjugation tables and synonym recommendations. Because example sentences originate from public multilingual corpora, users should assess context suitability for sensitive or formal drafts.

Its document portal, Reverso Documents, accepts PDF, Word, PowerPoint, Excel, and select localization files. It provides an in-browser segment-by-segment review interface where teams can collaborate on edits before downloading the completed file.

Reverso web translation interface and navigation bar.

Yandex Translate

The Yandex Translate web portal and mobile apps handle text, images, websites, and documents. Its Android client includes a detailed dictionary that displays phonetic transcriptions, definitions, synonyms, and morphological inflections for supported languages.

On mobile, the Android app comes with a pre-installed English-Russian offline dictionary, while additional language packs can be downloaded for offline typed text translation. The desktop interface accommodates standard Office and PDF uploads. Note the distinction between Yandex Translate as a standalone service and Yandex Browser, which houses proprietary automatic video voiceover features.

Yandex Translate input interface and side navigation.

3. Complex Document Layouts & Enterprise Workflows: Preserving Formats and Assets

When translating commercial agreements, slide decks, or technical manuals, broken formatting leads to hours of manual re-layout. These services prioritize layout preservation, terminology consistency, and data security.

DeepL

DeepL Translator offers granular configuration for text and document translation. Users can build custom Glossaries to enforce corporate vocabulary, and toggle between formal and informal tone registers in supported languages.

Its document translation service accepts Word, PDF, PPT, Excel, HTML, and SRT files (with format access varying by account type). The product ecosystem also includes DeepL Write for text polishing, DeepL Voice for Online Meetings for real-time captions on Teams and Zoom (requiring Voice licensing and host permissions), and an official Model Context Protocol (MCP) guide for AI agents.

DeepL web translator interface.

O.Translator

O.Translator focuses on layout-preserving document translation. In addition to PDF, Word, PPT, and Excel, it supports publishing and localization formats such as EPUB e-books, InDesign (IDML), Illustrator (AI), OpenDocument, subtitle files (SRT/ASS), and comic archives (CBZ/CBR), with built-in OCR for scanned pages. Layout accuracy depends on font embedding and target text expansion.

Before translating an entire file, O.Translator allows users to inspect a partial layout preview. It supports importing glossaries via XLSX or TBX, and provides a developer API. Its media option is designed for transcribing uploaded audio and video files into subtitle files, rather than real-time browser stream translation.

O.Translator homepage and document upload section.

SimplifyAI

SimplifyAI operates two distinct portals: an AI-driven Complex Document Workbench and a General Document Translation portal.

Within the workbench, the system can extract high-frequency terms prior to translation for user review across Word, PPTX, InDesign, PDF, and EPUB files. The workbench also provides AI Editing for Word and InDesign (supporting native Word track changes), bilingual data export (Excel/XLIFF), structured Markdown/JSON extraction, and visual checks for text overflow and font layout, making it well-suited for prepress and design asset localization. For straightforward everyday file translation, the general translation portal offers a simpler direct flow.

SimplifyAI homepage showing its complex document workbench and modules.

Lingvanex

Lingvanex provides desktop, mobile, and browser clients across Windows and macOS. Its Windows desktop translator supports system-wide shortcuts (such as double-tapping Ctrl+C on highlighted text) and allows offline text and local DOCX/ODT file translation after downloading language packs.

Beyond consumer applications, Lingvanex offers downloadable Secure Translation Software desktop software for offline enterprise use, as well as separate On-premise Machine Translation solutions for private network environments.

Lingvanex homepage featuring enterprise translation and on-premise solutions.

SYSTRAN

SYSTRAN targets enterprise and institutional localization requirements. Its cloud service, SYSTRAN Translate Pro, is available immediately for Word, PowerPoint, Excel, and PDF files, offering pre-configured domain models for legal, financial, and industrial documentation alongside custom glossaries and translation memory (TM).

For organizations with data sovereignty requirements, SYSTRAN provides Translate Server for on-premise deployment behind corporate firewalls, dedicated Private Cloud environments, and batch APIs for document pipelines.

SYSTRAN Translate Pro official product overview interface.

4. Academic Writing, Refinement & Collaborative Editing: Polishing the Output

Translation in academic and publishing contexts is rarely a single-shot operation. Researchers and writers need dictionary validation, grammar checks, and human-in-the-loop phrase tuning.

Youdao Translate (NetEase Youdao)

Connecting with NetEase Youdao's dictionary ecosystem, Youdao Translate links vocabulary lookup, translation, and writing assistance. In addition to standard text and file translation, its web portal offers dedicated entries for "arXiv Paper Translation" and academic text polishing.

After translating research excerpts, users can run grammar checks, evaluate synonym choices, or adjust academic tone, helping students and researchers review foreign literature and draft manuscripts. Format and language scopes for paper polishing and media modules differ from the general dictionary lookup.

NetEase Youdao Translate web interface and feature navigation.

Baidu Translate

Baidu Translate provides broad client coverage for Chinese-speaking users. Its desktop software features a compact floating window and shortcut text selection across local desktop apps, while its mobile app combines photo translation, spoken practice, and dictionary references.

In addition, Baidu hosts a standalone Baidu Video Translation portal. Users upload media files to generate aligned bilingual subtitle tracks, review and edit them in an online editor, and export finalized subtitle files. This is an upload-based post-production tool rather than an automatic interpreter for live web playback.

Baidu Translate official web interface.

TranSmart (Tencent Interactive Translation)

Developed by Tencent AI Lab, TranSmart is designed around interactive human-machine collaboration. Rather than generating a static output for copying, TranSmart suggests word-level and sentence-level predictive completions in real time, integrating confirmed bilingual pairs into active translation memory.

Translators can place their cursor anywhere in the translated text to make adjustments, prompting the system to refresh downstream suggestions dynamically. This keeps terminology decisions and sentence pacing in the hands of the user, operating as a collaborative editor distinct in focus from Tencent's standalone consumer dictionary mobile apps.

Tencent TranSmart official web interface.

LingoCloud (Caiyun Xiaoyi)

LingoCloud is widely used for Chinese, English, and Japanese workflows. Its browser extension delivers bilingual in-page web reading with shared public and personal glossary support. Its document translation service accepts formats like PDF, Word, PPT, Excel, EPUB, TXT, and SRT, delivering downloaded outputs primarily in PDF or Word format depending on the source file.

Its desktop software also features LingoCloud Interpretation, which can capture microphone audio or intercept system audio output from running applications (such as Zoom, Teams, or Chrome on Windows) to render live dual-language subtitles. Desktop interpretation is subject to operating system audio capture boundaries: on Windows, system audio capture works across supported conference and media apps; on macOS, internal system audio recording routes are currently unsupported due to macOS system updates, leaving microphone capture as the operational route.

LingoCloud official web interface.

QuillBot Translate

QuillBot Translate operates within QuillBot's writing and editing ecosystem. When translating text, the interface provides formality options and displays definitions and synonyms in supported languages.

Translated text can be copied smoothly into its Paraphraser and Grammar Checker to refine sentence flow. The platform also maintains a dedicated Translate PDF page for uploading and reviewing single PDF documents. Supported languages vary between the translation, grammar, and paraphrasing tools.

Official Chrome Web Store product page for the QuillBot browser extension.

5. Open-Source Ecosystem: Scientific PDFs, Self-Hosted Engines & Desktop Frontends

Developers, privacy-conscious engineering teams, and academic researchers often need inspectable source code, offline execution, or custom automation pipelines. The open-source translation ecosystem spans several distinct architectural layers:

Important Architectural Note: Running open-source software locally does not necessarily mean your data remains offline. Many tools run locally as client frontends while querying remote cloud APIs by default. Truly offline, air-gapped translation requires both local model weights and a local neural execution engine.

5.1 Scientific & Academic PDF Pipelines

PDFMathTranslate (pdf2zh)

PDFMathTranslate (GNU AGPL v3) is an open-source tool tailored for scientific and academic PDF documents. It preserves multi-column paper structures, mathematical notation, embedded graphics, tables of contents, and annotations.

Dual and Mono Outputs: Generates both translated-only (-mono.pdf) and bilingual comparison (-dual.pdf) documents.
Interfaces & Integrations: Provides command-line tools (CLI), an interactive WebUI, Docker container deployment, and Model Context Protocol (MCP) support. A linked Zotero integration plugin is available as a companion project.
Translation Backends: Employs a pluggable architecture supporting Google Translate (documented default), DeepL, OpenAI-compatible APIs, and local Ollama instances. Local deployment via Docker or WebUI does not imply offline operation if cloud backends are configured.
OCR Support: Includes experimental OCR for black-text on white-background scanned pages (downloads language model assets on first use, which can then be reused locally).

Official PDFMathTranslate repository overview illustrating academic PDF layout translation and CLI/WebUI workflows.

BabelDOC

BabelDOC (GNU AGPL v3) is a document-level scientific paper translation and bilingual comparison library, designed primarily to be embedded into Python applications, accompanied by a debugging CLI.

Layout & Output Control: Supports mono or dual outputs, same-page side-by-side or alternating original/translated pages, selective page translation, splitting and merging large PDFs, custom glossary CSV input, and formula preservation. Table text translation is explicitly documented as experimental.
Backend Architecture: Requires a configured translation backend via OpenAI-compatible endpoints or a local Ollama instance. As a PDF processing and layout engine, it does not bundle a universal translation engine itself.
Offline Assets & Boundaries: Provides warmup routines and offline asset generation/restoration for document layout models and fonts. Fully offline execution requires both pre-cached assets and a locally running translation backend (such as local Ollama). Documentation highlights primary validation on English-to-Chinese workflows, with an experimental OCR workaround for black text on white backgrounds.

Official BabelDOC repository overview demonstrating document-level scientific PDF translation library capabilities.

5.2 Self-Hostable Engines & APIs

LibreTranslate

LibreTranslate (GNU AGPL v3) is a free and open-source self-hostable machine translation API service with an included web UI, built on top of the Argos Translate engine.

API & Web Service: Exposes REST API endpoints for text translation, source language detection, and HTML/markup handling. It functions as an independent service layer rather than a proxy to commercial translation APIs.
Local Deployment & Privacy: Can run completely on local hardware without sending data to external third parties once dependencies and language models are installed. Using a public hosted instance remains network-dependent. API key access control can be enabled or disabled according to host requirements.
Language Coverage & File Formats: Available language pairs depend on installed language models. Through companion projects like argos-translate-files, file translation supports formats including TXT, ODT, ODP, DOCX, PPTX, EPUB, HTML, SRT, and PDF.

Official LibreTranslate repository overview showing self-hosted translation API and web interface features.

Argos Translate

Argos Translate (MIT License / CC0 option declared in README) is an open-source offline Python translation library and command-line tool, with a separately installable GUI client.

Modular Model Packages: Downloads and manages language model packages using the .argosmodel extension. When a direct language pair is unavailable, it can pivot through installed intermediate pairs (e.g., translating through English).
Ecosystem Engine: Serves as the underlying machine translation engine for LibreTranslate. Companion projects extend its capabilities to HTML translation (translate-html) and file processing (argos-translate-files).
Offline Operation: Runs fully offline once models are installed; downloading package indices and initial models requires internet connectivity.

Official Argos Translate repository overview detailing the modular offline translation engine and package system.

5.3 Desktop & Terminal Frontends

Pot (pot-desktop)

Pot (GNU GPL v3) is a cross-platform desktop translation tool for Windows, macOS, and Linux, supporting selection translation via hotkeys, typed input, clipboard monitoring, screenshot OCR, and screenshot translation. The upstream repository was archived by the owner on September 7, 2026, and is now read-only.

Multi-Service Aggregation: Allows querying multiple translation and dictionary services simultaneously to compare results side-by-side. Supports text-to-speech (TTS), vocabulary export to Anki and Eudic, and plugin extensions.
Pluggable Backends & OCR: Aggregates cloud translation providers, OpenAI-compatible APIs, and local Ollama endpoints. OCR choices include platform-native options (Windows system OCR, Apple Vision, Linux Tesseract), Tesseract.js, or local plugins.
Offline Execution Routes: Selection and typed text translation require only a configured local translation backend (such as a local Ollama instance); screenshot translation additionally requires an offline OCR engine (such as platform-native OCR or Tesseract). Cloud services route requests over the network.

Official Pot desktop client repository overview highlighting multi-interface translation, OCR, and clipboard workflows.

Translate Shell

Translate Shell (The Unlicense / Public Domain) is a versatile command-line translation tool (executable trans) for Unix-like terminal environments.

CLI Lookup & Dictionary: Supports word definitions, phrase translation, concise dictionary mode, interactive REPL sessions, and language identification directly in the shell.
Unix Pipelines: Integrates with standard input/output (stdin / stdout), processes text files directly, and supports speech synthesis when an external audio player is installed.
Engine Layer: Operates as a lightweight client front end connecting to public translation services (Google Translate by default, Bing Translator, Yandex.Translate, and Apertium).
Boundaries: Does not bundle local neural translation models; standard operation depends on external network connectivity to selected engine services. File translation is designed for plain text streams, not formatted documents.

Official Translate Shell repository overview showing terminal command-line translation and pipeline integration.

6. Connected End-to-End Workflows: Equalang

Examining these individual tools demonstrates that each product has solved specific parts of the translation challenge. In modern workflows, however, requirements frequently intersect:

A developer might read foreign documentation in a browser, download an accompanying slide deck containing editable tables, review an uncaptioned technical talk on YouTube, and coordinate with overseas partners over a live call. Constantly switching between disparate tools, browser tabs, and file converters causes friction.

We built Equalang to unify these tasks into a continuous, side-by-side workflow across documents, web pages, videos, and live spoken communication.

Equalang official English website homepage.

1. Whole-File Document Translation with Layout Preservation

Equalang focuses on preserving structure and document editability across slides, papers, spreadsheets, and e-books:

PowerPoint Presentations: As detailed in our slide deck formatting guide, translated PPTX files preserve native editable tables rather than flattening them into static images. Word-level styling—such as bolding, italics, and font colors within a single sentence—is accurately mapped to corresponding translated phrases. Key terms and headings remain consistent across slides, and text boxes automatically scale down font sizes when translations expand to prevent text overflow or covering graphics.
PDF Documents & Reading: Equalang preserves multi-column layouts, headers, footers, and captions, reconnecting sentences split across page breaks before translating, while maintaining table structures, inline formulas, and internal document links. In our academic PDF reading walkthrough, readers can view the translated file alongside the original in a side-by-side layout.
Word & Excel Office Files: In our verified Word translation test, translated DOCX files retained headings, bulleted lists, pricing tables, and bold formatting, allowing direct editing in Microsoft Word. In our Excel price sheet validation, formulas and numbers remained untouched while duplicate text strings across cells were translated only once.
E-Books & Formatted Media: EPUB e-books retain table-of-contents navigation and internal anchor links. For recorded audio and video files up to 180 minutes, translation and transcription tasks are submitted via our Developer API and Agent Skill/MCP integration (rather than a general web document upload portal), outputting timestamped bilingual SRT/VTT subtitle files or source transcripts.

2. In-Browser Reading & Subtitle Generation

Through our lightweight browser extension (with installation guides for Chrome, Edge, and Firefox, plus a temporary Mac Safari mode for Safari 18.4+):

Under-Paragraph Bilingual Web Reading: Translated paragraphs appear directly beneath the original text as you scroll. A floating icon can be toggled in settings for on-demand word lookups. When viewing local PDFs, users can enable "Allow access to file URLs" in extension management to select words for lookup.
Bilingual Video Subtitles: Compatible with YouTube, Netflix, TikTok, and Bilibili, as explored in our bilingual video viewing guide. Beyond translating existing subtitles, the extension can capture audio streams to generate real-time bilingual subtitles for uncaptioned videos (subject to browser environment and media encryption limits, verified on YouTube live streams and official trailers), while simultaneously translating live chat comments on YouTube.

3. Installation-Free Spoken Communication & On-Site Exchange

Requiring conversational partners to install dedicated mobile applications creates friction, especially while traveling. When connected to the internet, Equalang delivers on-the-go photo translation and spoken interpretation directly inside standard browsers (requiring only an initial sign-in and device camera/microphone permission on first use), as outlined in our international communication guide:

Mobile Photo Translation: When encountering unfamiliar restaurant menus, signs, or public notices while traveling, users can snap a picture in their mobile browser. Translations overlay directly onto the photo layout, making it easy to order drinks or review notices against the original image.
Face-to-Face Mode: Designed for in-person situations such as hotel luggage storage, asking directions, or front-desk interactions. Two speakers can place a single phone or tablet flat between them, using an inverted split-screen or side-by-side view with continuous two-way transcription and transcript export.
Live Listening: Open the web portal during an in-person presentation or lecture to receive real-time bilingual subtitles captured via the device's physical microphone, with optional text-to-speech audio and transcript export when finished.
Translated Calls: Hosts log in on the web portal to generate a secure call link and share it via any messaging app. Guests join directly through their browser without creating an account or installing any software—they simply enter a display name and the host admits them to begin the call. Both parties speak their native language, hear translated audio, and view real-time text.

4. Integration for AI Agents and Developers

To help developers and engineering teams embed translation into automated workflows:

Developer API: Features instant endpoints for text alongside asynchronous file jobs supporting Idempotency-Key retries and callback notifications, as detailed in our file translation API integration guide.
Skill & MCP Integration: We maintain open-source Agent Skills via equalang-skill and official Model Context Protocol support via @equalang/mcp. In environments such as Claude Code, Codex, or WorkBuddy, running a single installation prompt and configuring your API key equips your AI assistant to handle document translation and media transcription directly within your workflow.

7. Task-Based Decision Guide

To help you quickly match the right tool to your immediate project, here is how the 26 tools align by primary task:

Primary Task	Core Requirement	Recommended Tools	Key Architectural Considerations
Travel & Spoken Dialogue	Photo OCR, two-way dialogue, offline packs	Google Translate, Apple Translate, Papago, Equalang	Download offline packs in Google, Apple, or Papago (noting hardware requirements) for weak-signal areas; when connected, Equalang provides browser-based photo translation and face-to-face dialogue without installing mobile apps.
Multi-Device Workshops	One-to-many presentations, multi-device participation	Microsoft Translator	Host runs Presenter mode via mobile app; attendees join via standard desktop or mobile browser without installing software.
In-Depth Web Reading	Under-paragraph reading without leaving the page	Immersive Translate, Equalang, Mate Translate	Use Immersive Translate or Equalang for bilingual paragraphs; use Mate Translate for switching full-page views or saving words to Phrasebooks on macOS.
Uncaptioned Video & Live Streams	Real-time subtitle generation, streaming compatibility	Equalang, Immersive Translate	Both tools can generate subtitles from raw audio on supported platforms (like YouTube); compare browser extension workflows for live chat and stream handling.
Academic Papers & Scientific PDFs	Formula preservation, column structures, cross-page text	PDFMathTranslate, BabelDOC, Equalang	PDFMathTranslate and BabelDOC provide open-source pipelines with dual-PDF output and local/cloud LLM backends; Equalang provides browser-based side-by-side reading and layout preservation.
Publishing Prepress & Design Formats	InDesign, Illustrator, comic archives, prepress QA	SimplifyAI, O.Translator	Use SimplifyAI and O.Translator for InDesign (IDML) and design asset prepress; SimplifyAI includes AI Editing with native Word track changes.
Presentations & Office Documents	Preserving native tables, styles, formulas, and editability	Equalang, DeepL	Equalang preserves PPTX native tables/styling with adaptive font sizing and Excel formula retention; use DeepL for corporate Word/Office files with glossaries.
Academic Writing & Polishing	Grammatical accuracy, formal scholarly register	Youdao Translate, QuillBot Translate, TranSmart	Youdao and QuillBot streamline translation into text refinement; TranSmart provides interactive human-in-the-loop editing.
Desktop Hotkey Lookup & Multi-Engine	Global shortcuts, OCR, comparing multiple engines	Pot, Mate Translate	Pot allows simultaneous multi-engine queries and screenshot OCR across Windows, Mac, and Linux; Mate offers a native Mac menu-bar utility.
Terminal Scripting & Shell Pipelines	CLI lookup, stdin/stdout pipelines, plain text scripts	Translate Shell, Argos Translate	Translate Shell provides lightweight CLI translation via remote engines; Argos Translate provides an offline Python CLI with local models.
Self-Hosted Private API & Offline Engines	Air-gapped networks, no third-party data transmission	LibreTranslate, Argos Translate, SYSTRAN, Lingvanex	LibreTranslate provides a self-hosted HTTP API service and WebUI; Argos Translate powers it as an offline Python library/CLI engine with modular model packages; SYSTRAN and Lingvanex offer enterprise on-premise deployments.
Connected End-to-End Workflows	Documents, streaming subtitles, web calls, and AI Agents	Equalang	Unified document processing, uncaptioned media subtitles, browser-based calls without app installation, and direct integration with Claude Code or WorkBuddy.

8. Directory Principles & Verification Criteria

To maintain practical utility and factual accuracy, entries follow strict criteria:

Documented Features Over Marketing Claims: Descriptions are derived from official documentation, user manuals, and confirmed repository source files. We do not claim perfect layout retention or universal format support.
Clear Architectural Boundaries: We distinguish between translation frontends, self-hostable service layers, offline translation engines, and document layout libraries. Open-source code running locally is explicitly separated from true offline execution.
Task-Oriented Coverage: Tools are grouped by practical suitability across workflows. We do not maintain subjective tier lists, quality rankings, or transient pricing figures.
Transparent Maintainer Identity: This catalog is curated and maintained by the Equalang team. Equalang is presented alongside peer tools with verifiable feature boundaries and transparent system requirements.