Can Jarvis Translate The Page I'm Looking At?

Yes. Because Jarvis (getjarvis.eu) is screen-aware, it can translate whatever is in your active window, a webpage, a PDF, an email, a Notion doc, without you copying anything. Summon the floating bar with Cmd+/ on macOS or Ctrl+/ on Windows and say "translate this page into English" (or any language). Jarvis reads the on-screen text, routes the job to frontier models from Anthropic, OpenAI, or Google, and returns the translation in the bar. You can then push it somewhere: reply in the translated language, or save it to Google Docs. It runs on macOS 12+, Windows 10+, and Linux. Your screen content is never used to train any model, and connector tokens are encrypted with AES-256-GCM at rest under GDPR. A the free weekly 40 requests run out, then Pro is $16/month and Unlimited is $32/month.

The advantage of screen awareness is that translation starts from what you are already viewing. Instead of selecting text, switching to a translator tab, and pasting, you press the hotkey and ask. This works even on content you cannot easily select, such as text inside an image-heavy page or a scanned PDF, because Jarvis reads the rendered screen. For a long document, you can ask it to translate just the section you point to or summarise-and-translate the whole thing into a few bullets in your language.

Translation in Jarvis rarely ends at the text itself. You can chain it: "translate this supplier email and draft a reply in their language" sends the response back through Gmail or Outlook; "translate this spec and create matching Linear issues" turns a foreign-language document into actionable tickets. Because the same instruction spans reading, translating, and acting across connectors like Slack, Notion, and Google Drive, the translated content moves directly into your workflow rather than sitting in a scratch window.

Capabilities