Skip to main content

Memory Translate Action

This action permits to pretranslate texts from memories.

The action is configured as follows:




string, Mandatory

The language of the text to find memory hits for. This is typically the source language of the segments.

string, Mandatory

The language into which we will write the memory translations. This is typically the target language of the segments.

string, Mandatory
similarityOptional, default is 100. The memory search similarity threshold. A value between 50 and 100 (100% = identical matches only).int, Optional

Optional, default is true.

  • true: Only copy if the target language does not already have a text
  • false: Always copy and replace existing target text


bool, Optional

An array of resource IDs. These are the resources we will scan for hits.

int[], Mandatory

Optional, default is false.

True: Ignore case when finding text pattern. False: Do not ignore lower/uppercase differences.

bool, Optional

Not yet released.

Optional. Specifies how top hits are selected and further permits to apply filters on various properties such as status, bookmarks, context, change date and so on.

"tmhits": {
	"filter": [
   		{ "field": "st", "values": [ 1 ] },
   		{ "field": "bk", "values": [ 1, 2 ] }
	"ctxboost": null

Read details here:

TM Filters and Sort (Object)



JavaScript errors detected

Please note, these errors can depend on your browser setup.

If this problem persists, please contact our support.