Skip to main content

Professional AI-enhanced translation workbench with multi-LLM support, termbase system, TM, spellcheck, voice commands, and PyQt6 interface. Batteries included (core).

Project description

Supervertaler Workbench

PyPI version Python 3.10+ License: MIT

Professional AI-enhanced translation workbench with multi-LLM support (GPT-4, Claude, Gemini, Mistral, Ollama), translation memory, glossary management, and seamless CAT tool integration (memoQ, Trados, CafeTran, Phrase, Déjà Vu).

See the latest release notes for what changed in the most recent build.


Download

Three ways to install. Pick whichever fits your setup.

Option Best for Get it
Pip (any OS, Python 3.10+) Developers and power users; smallest download; updates with one command. pip install --upgrade supervertaler then run supervertaler
Windows standalone (.zip) Windows users who don't want to install Python. Self-contained, ~470 MB. Download from the latest releaseSupervertaler-vX.Y.Z-Windows.zip
macOS standalone (.dmg) Apple Silicon Macs (M1 / M2 / M3 / M4). Code-signed and Apple-notarised, opens without Gatekeeper warnings. Download from the latest releaseSupervertaler-vX.Y.Z.dmg

Notes

  • macOS Intel: there's no Intel standalone build. Run from source after installing system Java 17 (brew install --cask temurin@17).
  • Linux: pip or run from source.

Run from source

git clone https://github.com/Supervertaler/Supervertaler-Workbench.git
cd Supervertaler-Workbench
pip install -r requirements.txt
python Supervertaler.py

Key Features

  • Supervertaler Sidekick - System-wide floating AI assistant (Ctrl+Alt+A from any app) with chat, text conversions, snippets, and prompt library actions
  • Multi-LLM AI Translation - OpenAI GPT-4/5, Anthropic Claude, Google Gemini, Mistral AI, Local Ollama, OpenRouter (200+ models)
  • Translation Memory - Fuzzy matching TM with TMX import/export
  • Glossary System - Project/Background glossary highlighting with forbidden term marking
  • Superlookup - Unified concordance search across TM, glossaries, MT, and web resources
  • CAT Tool Integration - memoQ XLIFF, Trados SDLPPX/SDLRPX, CafeTran, Phrase, Déjà Vu X3
  • Voice Commands - Hands-free translation with OpenAI Whisper
  • Document Support - DOCX, bilingual DOCX/RTF, PDF, Markdown, plain text + built-in Okapi Framework sidecar for industry-standard file extraction and round-trip export with full formatting preservation

Documentation

Resource Description
Online Manual Quick start, guides, and troubleshooting
Changelog Complete version history
Keyboard Shortcuts Shortcut reference
FAQ Common questions
Similar Apps CotranslatorAI, TransAIde, TWAS Suite, and other translation tools
Website Project homepage

Requirements

  • Python 3.10+
  • PyQt6
  • Windows, macOS, or Linux

Contributing

Translations

Supervertaler Workbench has an early-stage i18n system (v1.10.208+). The menu bar, Settings tabs, and key group titles are translatable; dialog bodies and error messages remain in English for now.

Translation files are XLIFF 1.2, so translators can open them in Trados, memoQ, Phrase, OmegaT, or Supervertaler Workbench itself – any CAT tool that handles XLIFF (all of them do).

Locale Language Status
en English source language
zh_CN 简体中文 — Simplified Chinese scaffold (sanity-translated samples)
zh_TW 繁體中文 — Traditional Chinese scaffold (untranslated)
pl Polski — Polish scaffold (untranslated)

Want to contribute a translation? See translations/TRANSLATING.md. Workflow: open the locale's .xlf in your normal CAT tool, translate, PR back. No build step on your end.


About

Supervertaler is maintained by Michael Beijer, a professional translator with 30 years of experience in technical and patent translation.

License: MIT - Free for personal and commercial use.


Current Version: See CHANGELOG.md for the latest release notes.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

supervertaler-1.10.228.tar.gz (21.1 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

supervertaler-1.10.228-py3-none-any.whl (1.5 MB view details)

Uploaded Python 3

File details

Details for the file supervertaler-1.10.228.tar.gz.

File metadata

  • Download URL: supervertaler-1.10.228.tar.gz
  • Upload date:
  • Size: 21.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.6

File hashes

Hashes for supervertaler-1.10.228.tar.gz
Algorithm Hash digest
SHA256 04b91cfad4534513a1cda9077b00f9f6c1be4689b05183f581686e1147c6c14a
MD5 4881fb0bca69a7ad77ff7d2b7dadbc32
BLAKE2b-256 9950ea4028a2466b8415ffa465f0eb054a8ca74c652279a530bc6c915e9d5e9d

See more details on using hashes here.

File details

Details for the file supervertaler-1.10.228-py3-none-any.whl.

File metadata

File hashes

Hashes for supervertaler-1.10.228-py3-none-any.whl
Algorithm Hash digest
SHA256 489828d3c5aa7402cd983bb5aaa28480fd6ff1a0278ba3c272c290415c86d0b4
MD5 1fe1336736a10174750109cee559d08f
BLAKE2b-256 971dc504b5874870459b583cc9cb41fcd72beb021907dafdf8bb0174411fa518

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page