Batch Translate

Batch Translate lets you translate multiple segments at once using AI. It is located in the Supervertaler Assistant panel, on the Batch Operations tab.

Note

The Batch Operations tab also supports Proofread mode for AI-powered quality checking. See AI Proofreader for details.

Starting a Batch Translation

1. Open the Supervertaler Assistant panel (View > Supervertaler Assistant)
2. Switch to the Batch Translate tab
3. Choose a scope from the dropdown
4. Choose a prompt from the prompt selector
5. Click Translate

Scope

The scope dropdown controls which segments are translated:

Scope	Description
Empty Segments Only	Translates segments that have no target text
All Segments	Translates every segment in the file
All unfinished segments	Translates every segment that isn’t Translated, Approved or Signed off – drafts and rejected segments included
Filtered Segments	Translates only the segments currently visible after applying a filter
Filtered Empty Only	Translates empty segments within the current filter

Note

Locked segments are never sent to the AI, in any scope – batch translation and batch proofreading both skip them, and the segment counters above the Translate button exclude them. (From v18.20.154; earlier versions incorrectly included locked segments in batch runs.)

Prompt Selection

Choose a prompt to guide the AI translation style and domain. The prompt selector shows, from the top:

• (Built-in instructions only) – no prompt from your library: Supervertaler’s own translation instructions alone (inline tags, numbers, the output contract), with your termbase, translation memory matches and memory bank as set in AI Settings.
• Default Translation Prompt – a general-purpose prompt that works well for most content types. Use it as-is or duplicate it in the Prompt Manager and customise it for your domain. From v18/19.20.200 this is what Batch Translate and Alt+T use until you choose another prompt; before that, they started on the built-in instructions alone.
• Custom prompts – your own prompts created in the Prompt Manager

Choosing (Built-in instructions only), or turning off the active prompt in the Prompt Manager, is remembered as your choice. Hover over the prompt selector for a summary of what each kind of item means.

The active prompt for the current project is marked with a checkmark in the dropdown. When you open a project that has an active prompt set, it is automatically selected. See Memory banks – Active Prompt for how to set the active prompt.

Tip

Tip: If you save a prompt with the same name as your Trados project, the dropdown will auto-select it whenever you open that project. For example, a prompt called “HAYNESPRO” will be auto-selected when working in a project called HAYNESPRO.

Note

For specialised fields (medical, legal, patent, etc.), create a custom prompt with domain-specific terminology rules and instructions. A tailored prompt is the single most effective way to improve translation quality.

Provider and Model

The current AI provider and model are displayed below the prompt selector. Click the provider/model label to open a flyout menu where you can switch models instantly – the same menu available in the Chat tab. Alternatively, open the settings dialogue (gear icon in the TermLens header) and go to the AI Settings tab.

Your custom OpenAI-compatible profiles (institutional gateways, self-hosted endpoints) appear at the bottom of the same menu under Custom (OpenAI-compatible), each showing its configured model, with the active profile ticked – so switching between custom endpoints is one click, no trip to Settings. (From v18.20.154.)

Progress and Logging

During translation:

• A progress bar shows overall completion
• A real-time log displays the status of each segment as it is translated
• The Stop button aborts the batch at any time – segments already translated are kept

Translate Active Segment (Alt+T)

Press Alt+T to translate the active segment instantly. This uses the same provider, model, and prompt as Batch Translate, so you can switch prompts or providers and immediately use them for single segments with Alt+T.

Alt+T is also available via right-click in the editor (“Translate active segment”).

Alt+T does nothing?

Trados also puts one of its own commands on Alt+T (Toggle between Source and Target in Translation Results View), and the Trados binding wins. Clear it once in File → Options → Keyboard Shortcuts and Alt+T works. See Keyboard shortcuts.

Note

Older installs may still have this on Ctrl+T – the default moved to Alt+T in v18/19.20.119 because Ctrl+T collides with a Trados factory shortcut. See Keyboard shortcuts for how to reassign it.

How it works

1. The active segment’s source text is sent to the AI provider configured in AI Settings
2. The selected prompt (from the Batch Translate tab) is applied, along with termbase terms
3. The same document context and SuperMemory context as a batch run is included (from v18/19.20.149 – earlier versions sent the segment on its own, which is why single segments used to translate noticeably worse than a batch)
4. The translation is written directly into the target cell
5. Inline tags (bold, italic, field codes, etc.) are preserved in the translation

In short: a single segment now gets everything a batch run gets, minus the other segments – same prompt, same terminology, same document context. On versions before 18/19.20.149, batch translating even small ranges gave better results than going segment by segment; from 18/19.20.149 the two are equivalent.

Cost when you go segment by segment (from v18/19.20.198). Everything that is the same for every segment – the instructions, the SuperMemory context and the document content – is sent identically each time, and only the segment and its own termbase terms change. Providers that cache prompts therefore store that shared part on the first segment and read it back on the next ones: on Claude, from the second segment on, it costs about a tenth of its normal price, as long as each segment follows the last within five minutes. On a typical job that makes every segment after the first roughly ten times cheaper than the first. Before 20.198 the segment’s terms sat in the middle of the shared part, so it was never reused.

What the Batch Translate log shows for Alt+T (from v18/19.20.198). How many of your AI-enabled termbase terms occur in the segment and go with it, and a warning when terms are loaded but no termbase has its AI column ticked in Settings → Termbases – in that case no terms are sent at all. A request that fails is reported there and, if you log AI calls to the Reports tab, recorded there too.

AI Context in Batch Translate

Batch Translate uses several context sources from your AI Settings to improve translation quality:

• Document content – when enabled, all source segments are included in the system prompt so the AI can determine the document type (legal, medical, technical, etc.) and adapt its style accordingly. This is shared across all batches.
• Termbase terms – terminology from enabled termbases is injected into the prompt, including term definitions and domains when that option is enabled.
• Custom prompts – the selected prompt provides domain-specific translation instructions.
• SuperMemory – when enabled, the active memory bank and _shared. From v18/19.20.198 a large bank is narrowed to the part the document needs, the first time you translate it, and the log says what was sent and names a file listing what was left out. See SuperMemory – AI Integration.
• Translation memory matches – Batch Translate searches the project’s translation memories for each segment and sends the closest match, together with the source sentence it was made for, so the AI can see which words differ instead of assuming the wording fits. From v18/19.20.198 a match is offered as a reference to check, not as wording to follow: a memory can hold translations made for other documents, products or clients, and they can be wrong, even at 100%. The AI reuses a match only where it is correct for the segment, lets the termbase and the document take precedence, and translates from the source when in doubt. Matches at or above Lowest TM match to send in AI Settings are sent, 70% by default. This works on empty segments too, not only ones Trados has pre-translated. Send TM matches to the AI on the Batch Operations tab turns it off for a job whose memory you do not trust, and 👁 Preview prompt shows the matches. (From v18/19.20.190; in Clipboard Mode from v18/19.20.198.)

Surrounding segments are not included in Batch Translate – that is a Chat & QuickLauncher feature. See the AI Settings page for a full comparison table.

What the AI may send back

(From v18/19.20.198.) Every translation request ends with a fixed output contract, whichever prompt is selected: the reply is the translation and nothing else – no preamble, no notes, no explanations, no alternatives, no markdown, every tag kept. A prompt can add to it but cannot switch it off by accident, because it comes last, after the prompt, the terminology, SuperMemory and the document. Preview prompt shows it at the end of the system prompt. Supervertaler for memoQ sends the same contract, so a prompt written for one product reads correctly in the other.

Every reply is checked against it before anything is written. A reply that carries more than the translation – a note after it, the model explaining its own choices, a remark about the translation memory, markdown or a line break the source does not have, a second [[TC: …]] marker – is asked for once more, with the contract restated. If the second answer does the same, nothing is written: the segment is left empty, and the Batch Translate log names it and gives the reason. Retry segments left empty does not send it a third time. An empty segment costs you one segment to translate yourself; a note in the target could reach your client. The same check applies to Translate active segment (Alt+T).

The check looks for signs of commentary that the source itself does not have, so a source that really does contain a label such as “Note:” or markdown is translated as usual. Text written in the first person passes too: Ik verklaar dat ik dit document heb vertaald can become I declare that I have translated this document, because the source has its own word for “I” and the translation adds no sentence to it. One case can still be refused wrongly: a source that leaves the pronoun out, as Spanish and Italian can (He traducido…, Ho tradotto…), translated into English. If the log gives the model writing about its own choices for a segment like that, translate it by hand.

Translator comments

Where a note is genuinely needed – a defect in the source, a real ambiguity, an error the AI corrected in a 100% translation memory match, a deliberate departure from the termbase – the contract gives the AI one place for it: a single [[TC: …]] marker at the very end of that segment’s translation, 5 to 20 words, written as your comment to the client, in English unless your prompt says otherwise. For example: [[TC: "100 000 miljoen euro" means EUR 100 billion. Please check.]]

Where it ends up is your choice, in Settings → AI Settings → Add the AI’s [[TC: …]] notes as Trados comments:

• Unticked (the default): the marker stays at the end of the target, where you see it while you review. Decide whether it is worth keeping, add it as a Trados comment on the words it is about, and delete it from the target before you confirm the segment. Search the target for [[TC: to find them all.
• Ticked: the marker is taken out of the target and added to the segment as a Trados comment. If Studio refuses the comment, the marker is written at the end of the target instead, so no flag is lost.

This applies to Batch Translate, Translate active segment (Alt+T) and Paste from Clipboard.

The Default Translation Prompt used to tell the AI it could “add a brief explanation in parentheses” when a term had no established equivalent, which a model can take as licence to explain itself in the target. From 20.198 it asks for a [[TC: …]] marker instead. Your copy is updated automatically unless you have edited it; an edited copy is left alone.

Backup TMX

The Auto-backup translations to TMX checkbox is ticked by default. When enabled, Supervertaler writes every translated segment to a TMX file as it arrives from the AI. If Trados crashes mid-run, you can recover the completed translations without re-running the batch.

The TMX files are also useful outside of crash recovery – you can import them into any TM in Trados, memoQ, Wordfast, or any other CAT tool that accepts standard TMX.

Click Open folder… next to the checkbox to open the backup folder directly in Windows Explorer.

To disable backups for a particular run, simply untick the checkbox before clicking Translate.

How it works

• A new .tmx file is created at the start of each batch run.
• Every 10 translated segments, the file is rewritten in full – so at most 10 segments are lost in a crash.
• The file is written atomically (via a temp file + rename) so it is always a valid, complete TMX – never a partial or corrupt file.
• At the end of a completed or cancelled run, the file is flushed one final time.

Where the files are saved

C:\Users\<YourName>\Supervertaler\trados\batch_backups\

Files are named by timestamp and project name, for example:

batch_2026-04-10_14-23-01_YAXINCHENG.tmx

The exact path is also printed to the Batch Translate log at the start of each run.

Recovering after a crash

1. Reopen Trados Studio and your project.
2. Open your TM in Trados Translation Memories (or via the project’s TM settings).
3. Use Import → browse to the backup .tmx file → import.
4. Run Pre-translate on your project to apply the recovered translations from the TM.

Note

Backup files are not deleted automatically. Tidy up the batch_backups folder occasionally if disk space is a concern, or keep them as a translation archive.

Clipboard Mode

If you prefer to use a web-based AI (ChatGPT, Claude, Gemini, etc.) instead of an API, tick the Clipboard Mode checkbox. This replaces the Provider and Translate button with Copy to Clipboard and Paste from Clipboard buttons. Supervertaler builds a complete, ready-to-use prompt – including your selected prompt, terminology, document context, and numbered bilingual segments – and copies it to your clipboard. See Clipboard Mode for full details.

Tips

Translate Empty Segments First

Start by translating only the empty segments (scope: Empty Segments Only). Review the results, then fix any issues. This avoids overwriting segments you have already edited.

Generate a Domain-Specific Prompt Automatically

Click AutoPrompt… next to the prompt dropdown. Supervertaler analyses your entire document, detects the domain, and uses AI to generate a comprehensive translation prompt with terminology rules, style guidelines, and anti-truncation controls – all tailored to your specific project. See AutoPrompt for details.

Create Domain-Specific Prompts Manually

For specialised content, you can also duplicate the Default Translation Prompt in the Prompt Manager and add domain-specific instructions (terminology rules, style preferences, formatting requirements). A tailored prompt is the single most effective way to improve translation quality.

Combine with TM

If your project has a translation memory, TM matches are shown alongside AI translations. You can pre-translate with TM first (using Trados’s built-in batch tasks), then use Batch Translate to fill in the remaining empty segments with AI.

Review After Batch

AI translation is a first draft. After a batch run:

1. Review each translated segment
2. Fix any terminology or style issues
3. Confirm segments with Ctrl+Enter (Trados default)

---

See Also

• Clipboard Mode
• AutoPrompt
• AI Proofreader
• Supervertaler
• TermLens
• SuperMemory
• Keyboard Shortcuts