XTM Cloud 26.2

If your XTM Cloud Administrator has connected DeepL Translator to your XTM Cloud instance, you can decide whether to enable or disable it for the relevant customer. Set the Use DeepL Translator checkbox to:

• cleared – to disable DeepL Translator for the relevant customer.

• selected – to enable DeepL Translator for the relevant customer.

  When you select this option, the DeepL Translator login data dropdown is displayed.

Select the value of the DeepL Translator login data setting:

• System default.

• Customer-specific.

  When you select this option, the additional Authentication key text field is displayed.

If your XTM Cloud Administrator has connected Google machine translation to your XTM Cloud instance, you can decide whether to enable or disable it for the relevant customer. Set the Use Google machine translation checkbox to:

• cleared – to disable Google machine translation for the relevant customer.

• selected – to enable Google machine translation for the relevant customer.

  When you select this option, the Use Google NMT and Use AutoML checkboxes and the Google MT login data dropdown is displayed.

Set the value of the Use Google NMT checkbox to:

• cleared – to disable the use of Google NMT.

• selected – to use Google NMT.

Set the value of the Use AutoML checkbox to:

• cleared – to disable the use of Google AutoML.

• selected – to use Google AutoML.

  When selected, the Use Google NMT checkbox is automatically selected and inactive.

Select the value of the Google MT login data setting:

• System default.

• Customer-specific.

  When you select this option, additional text fields is displayed:

  • Service account email – email address for the customer's Google service account.

  • Service account private key – private key for the customer's Google service account.

  • Project ID – ID of the customer's project in your Google account.

To view the List of synchronized models, select View models. The AutoML models popup, containing the following information about models, is displayed:

• Model name.

• Source language.

• Target language.

To view the List of synchronized glossaries, select View glossaries. The Google NMT and AutoML glossaries popup is displayed. In it, you see:

• Unidirectional glossaries displaying the following information:

  • Glossary name.

  • Source language.

  • Target language.

• Equivalent term sets section displaying the following information:

  • Glossary name.

  • Languages.

Valid values:

• cleared – to disable OpenAI GPT for the relevant customer projects.

• selected – to enable OpenAI GPT for the relevant customer projects.

  When you select this option, the OpenAI GPT login data setting is displayed.

From the OpenAI GPT login data dropdown, you can select:

• System default (default).

• Customer-specific.

  When you select this option, the LLM configuration section is displayed. In it, if required, enter customer-specific LLM credentials. For details, see Customer Editor – Settings: LLM Configuration.

Select the appropriate setting for the Use AI Translate & TQI checkbox:

• cleared – by default, the AI Translate & TQI feature is deactivated for all new projects created for this customer. If required, you and other Project Managers can activate the feature at project level.

• selected – by default, the AI Translate & TQI feature is activated for all new projects created for this customer. If required, you and other Project Managers can deactivate the feature at project level. When you select the checkbox, the AI Translate & TQI settings and the Confidence threshold setting are displayed.

Select the appropriate option from the AI Translate & TQI settings dropdown:

• System default (default) – the Confidence threshold section displays the system default values in read-only mode.

  Note

  If you use an XTM-provided LLM subscription, you must purchase an AI Words allowance for your entire XTM Cloud instance. For more information, contact your account manager.

  XTM uses ChatGPT and Gemini to run the AI Translate & TQI feature. To check which models are currently used, see the Supported models section in https://xtm.ai.transifex.com/docs#section/LLM-Configuration.

• Customer-specific – the Confidence threshold section displays the system default values, but they can be adjusted, if required.

  When you select this option, the LLM configuration section is displayed. In it, if required, enter customer-specific LLM credentials. For details, see Customer Editor – Settings: LLM Configuration.

  If you are using your own LLM keys, you must connect your XTM Cloud instance to at least one of the supported LLMs (for details, see LLM Configuration tab).

  If you are using GPT through Azure, the Deployment names setting is displayed. Use it to select two deployment names. It is required even, if you use both LLMs GPT and Gemini to run the feature. We recommend that you use one deployment name for a small model (for example, 4o-mini) and one for a large model (for example, 4o). Two deployment names are required to obtain the best quality results.

  Note

  If you are using your own LLM keys, the size of the source text, terminology, TM records, context segments, and the Style guide instructions can influence the LLM usage costs. For details, refer to your LLM subscription rules.

Use the Confidence threshold section settings to specify the minimum quality score for acceptable or good translations:

• Unacceptable – set a threshold below which segments are considered poor quality and need correction or post-editing by a Linguist. To do so, enter a numeric value in the text field. Alternatively, use the slider displayed above the Unacceptable label: the corresponding numeric value is displayed automatically in the text field. The Unacceptable quality range is marked in red on the slider. Target segments within this range are also marked in red in XTM Workbench. The default value is 0%.

• Acceptable – set a threshold to create a range for medium-quality segments. These LLM-translated segments meet basic standards, but a Linguist might need to make minor improvements to them. To set the threshold, enter a numeric value in the text field. Alternatively, use the slider displayed above the Acceptable label: the corresponding numeric value is displayed automatically in the text field. The Acceptable quality range lies between the Unacceptable threshold, or 0% (if the Unacceptable threshold has not been set), and the Acceptable threshold value. It is marked in yellow on the slider. Target segments within this range are also marked in yellow in XTM Workbench. The default value is 0%.

• Good – the setting value is fixed at 100%. Segments in the range between the Acceptable threshold, Unacceptable threshold (if Acceptable has not been set), or 0% (if neither the Acceptable nor Unacceptable threshold has been set), and 100% are considered high quality. They do not need corrections or post-editing by a Linguist. The Good quality range is marked in green on the slider. Target segments within this range are also marked in green in XTM Workbench.

  Important

  To ensure the best possible AI-generated translation quality, we recommend that you select the 95–100% Good quality range.