Description:

The Translate Text (Azure ML Language Translator) step enables a FlowWright workflow to translate text in real time by using Microsoft Azure Cognitive Services Translator.

Many business processes involve multilingual users, customers, suppliers, and partners. This step accepts source text, optionally accepts the source language, translates the content into a selected destination language, and stores the translated result in a workflow variable or global variable.

Unlike manually translating business content, this step automates multilingual communication within workflows and integrates seamlessly with Azure Cognitive Services. The source language defaults to AutoDetect, allowing Azure Translator to automatically determine the input language when one is not explicitly selected.

The translated output can then be incorporated into emails, workflow forms, notifications, reports, generated documents, REST API requests, or other downstream workflow activities.

Typical uses include:

• Translating workflow notifications
• Localizing customer communications
• Creating multilingual workflow forms
• Translating approval comments
• Translating chatbot or AI responses
• Preparing multilingual reports
• Translating document content before publishing
• Supporting multilingual integrations with external applications

This step enables organizations to automate multilingual business workflows while leveraging Microsoft's enterprise translation platform.

Usage:

The Translate Text (Azure ML Language Translator) step is typically used before sending multilingual communications or generating localized business content.

During execution:

1. Read the source text.
2. Determine the source language. If no language is explicitly selected, Azure Translator uses AutoDetect.
3. Submit the text to Azure Cognitive Services Translator.
4. Translate the content into the selected destination language.
5. Store the translated result in the configured workflow variable or global variable.
6. Continue workflow execution through either the True or False return path.

A typical workflow might look like this:

Typical workflow scenarios include:

• Translating customer support responses
• Localizing approval notifications
• Preparing multilingual reports
• Translating AI-generated responses
• Creating multilingual workflow forms
• Translating portal content
• Preparing multilingual REST API payloads
• Translating document metadata before publishing

To use this step, you need to set up an Azure ML service in the FlowWright application. Go to the Status > Settings > Configuration page. Select the Azure ML category from the drop-down menu. Click here to learn more about the Azure ML and Cognitive Service subscription. 

A sample Azure ML configuration is provided here for reference. 

Example:

Let’s build and execute the “clsAzureMLLanguageTranslatorDef” example. 

• Create a new process definition named “clsAzureMLLanguageTranslatorDef” and open it in designer mode. 
• Drag a "clsAzureMLLanguageTranslator" step to the canvas.
• Connect the dots between the “Start” and “clsAzureMLLanguageTranslator” steps, as shown above.
• Define a variable or a global to store the result.
• Click the "clsAzureMLLanguageTranslator" step to configure its "Required" properties. Provide a name for the step. Enter the text to translate. Select the target language from the drop-down list. Provide a variable or global reference to store the result. Click the Save button. Note: Click the "AI Predict" button for the Copilot to add new process steps that match your process description. 
   

• Click the "clsAzureMLLanguageTranslator" step to configure its "Optional" properties. Select the source language from the drop-down list, or let the application auto-detect it using the default setting. Click the Save button. 

• The “Logging” configuration is necessary for documentation and also measures workflow progress and percent complete. This is achieved by configuring the step state and percent fields individually, as shown in the images below. Configure the “Logging” using the following properties.

• Save the process definition, create a new instance, and run it. Render the process instance. Click the process step to view its properties. The step should translate the text into the selected language, and store the result in “variable.Result” as configured. 

Tips:

• Use the default AutoDetect option when the source language is unknown or may vary between workflow executions.
• Specify the source language when it is known to improve translation performance and consistency.
• Store translated text in reusable workflow variables for downstream workflow activities.
• Validate destination language selections before runtime when supporting multiple locales.
• Route the False execution path to logging and notification activities for easier troubleshooting.
• Combine this step with Send Email, Ask AI, Generate PDF, REST Call, Update Variable Values, or document generation steps to build multilingual enterprise workflows.

Notes:

• The step accepts multiline text input.
• The Select From Language property is optional and defaults to AutoDetect.
• The destination language is required.
• The translated text is stored in the configured workflow variable or global variable.
• The original source text is not modified.
• Both the True and False return paths should be implemented to provide complete workflow handling.
• Ensure that Azure Cognitive Services Translator is configured and accessible before executing this step.
• Translation execution details are recorded in the FlowWright workflow execution log.

Translate Text (Azure ML Language Translator) vs. Translate Text (Google Translate):

Although both workflow steps provide automated language translation, they integrate with different cloud translation platforms.

As a general guideline:

• Use Translate Text (Azure ML Language Translator) when your organization standardizes on Microsoft Azure Cognitive Services or when automatic source language detection through the default AutoDetect option is beneficial.
• Use Translate Text (Google Translate) when your FlowWright environment is integrated with Google Cloud translation services or when Google Translate is the preferred translation provider.

Definition Sample:

You may download the sample workflow definition from the link provided and import it into your FlowWright environment.

Note: Verify and complete any missing configuration after importing the sample, including:

• Source text
• Source language (or use the default AutoDetect option)
• Destination language
• Workflow variable or global variable for the translated text
• Success and failure workflow branches
• Azure Cognitive Services Translator configuration and credentials

After verifying the configuration, save and publish the workflow before execution.

Click here to download the sample file.