Translation workbench
A two-pane translation workspace in the dashboard — source and target side by side, with on-device, local, or cloud runtimes and streaming, layout-preserving output.
The translation workbench is a dedicated, side-by-side workspace for translating longer text. Unlike the quick floating-menu translate action, the workbench gives you a full source/target layout, a choice of runtime, and streaming output that preserves the paragraph structure of your source.
Opening it
Open it from the dashboard (nav → Translate), or from the chat header's Open translation workbench action.
Layout
The workbench is a two-pane grid:
- Source (left) — an editable text box where you paste or type what you want translated.
- Target (right) — a read-only box where the translation streams in.
Above the output, Cordy shows the detected source language and a data-flow label telling you whether this translation is running On-device, on a Local model, or in the Cloud.
Choosing languages
Pick a Source and Target language from the selectors. Source includes Auto (detect automatically); the target must be a specific language. The available languages are English, 简体中文 (Simplified Chinese), 繁體中文 (Traditional Chinese), 日本語 (Japanese), 한국어 (Korean), Français, Deutsch, Español, Português, and Русский.
Runtimes
A three-way toggle chooses where the translation runs:
| Runtime | What it uses | Data flow |
|---|---|---|
| Default | Chrome's built-in Translator API (on-device) | On-device |
| Local | A WebGPU local model you've selected | Local model |
| Cloud | A configured cloud provider and model (BYOK) | Cloud |
Default needs nothing beyond a supported Chrome. Local and Cloud require you to pick a model first — Cordy prompts you if you haven't. Local runtimes depend on local & on-device AI being set up; Cloud uses your provider keys.
Translating
- Choose your runtime and languages.
- Paste or type into the Source pane.
- Click Translate.
The translation streams into the target pane. For longer text, Cordy splits the source into chunks along paragraph and sentence boundaries (it's aware of both CJK and Latin punctuation) and reassembles the result so the original paragraph and line-break structure is preserved. A progress indicator shows how many chunks are done, and a status label moves through queued → running → completed (or stopped / failed).
Actions
| Action | What it does |
|---|---|
| Translate | Start translating the source |
| Stop | Halt an in-progress translation (partial output is kept) |
| Retry | Re-run the translation |
| Copy | Copy the translated text |
| Clear | Empty the panes to start over |
Notes and limits
- Layout preservation is plain-text. Cordy keeps paragraphs and line breaks, but the panes are plain text — Markdown, HTML, and rich formatting aren't reconstructed.
- No swap button. There isn't a one-click "swap source and target" in this version; set the languages directly.
- Local and Cloud need a model. Select a local or cloud translation model before translating with those runtimes.
Privacy
Where your text goes depends on the runtime you pick:
- Default (on-device) and Local never leave your device.
- Cloud sends your source text to the provider you configured — and the first cloud translation is covered by the one-time consent dialog.
Related
- Floating menu — quick inline translation of a selection.
- Local & on-device AI · Providers & models · Privacy & permissions