<aside>

Description

SimpleT Detect Language provides automatic language identification for Salesforce Flows and Apex code. It returns confidence scores and ranked language results to support content routing, workflow triggering, and multilingual processing.

</aside>

SimpleT Language Detection Options

• Flow-based language detection: Set up detection with declarative, no-code tools in Salesforce Flows.
• Apex-based language detection: Use full programmatic control in Apex for custom apps and integrations.

Setup

Use these guides to prepare your org before using SimpleT Detect Language:

• Install SimpleT Managed Packages - How to install a package?
• Authentication and Settings - How to set up your Salesforce org?
• Edit Record Page - How to edit the record page?
• Using SimpleT Flow Actions and Components - How to use SimpleT in Flows?

What You Can Do

Language detection capabilities

• Automatic language identification – detect which language any text is written in.
• Confidence scoring – get reliability scores for each detected language.
• Multiple language results – see a ranked list of possible languages.
• Batch text analysis – analyze multiple texts in one call.
• Smart content routing – route content based on detected language.
• Real-time results – detect language immediately within Flow or Apex.

When to use language detection

• Customer support – route tickets based on the customer's language.
• Content management – categorize documents by language.
• Survey analysis – group feedback by language.
• Email processing – identify the language of incoming emails.
• Social media monitoring – analyze posts and comments by language.
• Translation preparation – identify the source language before translation.

Detection Parameters Explained

Required fields

Detection Engine

• What it is: The language detection service to use.
• Available options (configured by an admin):
  • "ST Google Translate Default" – Google Cloud Translation.
  • "ST DeepL Default" – DeepL language detection.
  • "ST AWS Default" – Amazon Comprehend.
  • "ST AI Default" – AI-powered detection.
  • Any custom engines defined by your administrator.
• How to choose: Ask your admin which engines are available and recommended.

List of Source Texts

• What it is: The text content you want to analyze.
• Format: List of text strings.
• Examples:
  • Single text: ["Hello, how are you today?"]
  • Multiple texts: [{!email1Text}, {!email2Text}, {!email3Text}]
  • From records: [{!$Record.Description}, {!$Record.Comments__c}]
• Character limits: Varies by engine (typically 1000–10000 characters per text).

Understanding Detection Results

Result structure

Each detection result includes details for each submitted text:

detectionResults[0].detected_lan[0].Languages[0].LanguageCode  // primary language
 detectionResults[0].detected_lan[0].Languages[0].Score         // confidence score
 detectionResults[0].detected_lan[0].TextIndex                  // which input text

Multiple language results

Detection often returns several possible languages ranked by confidence:

Primary (highest confidence):   {!detectionResults[0].detected_lan[0].Languages[0]}
Secondary:                      {!detectionResults[0].detected_lan[0].Languages[1]}
Tertiary:                       {!detectionResults[0].detected_lan[0].Languages[2]}

Apex-based language detection

To use the ST_DetectLanguageInvocable class and its method, create a list of ST_DetectLanguageWrapper items with the required data.

For details on ST_DetectLanguageWrapper, see the class section below.

// Create a list of text values whose language you want to detect.
List<String> texts = new List<String>();

// Add texts to the list.
texts.add('Hello');
texts.add('Help');

// Create the wrapper that holds all data for the language detection callout.
simpleT.ST_DetectLanguageWrapper stDetectLanguageWrapper =
	new simpleT.ST_DetectLanguageWrapper();

// Add the prepared list of texts to the wrapper.
stDetectLanguageWrapper.texts = texts;

// Select the engine for language detection.
stDetectLanguageWrapper.engine = 'ST Google Translate Default';

// Invocable methods require a list of wrappers.
List<simpleT.ST_DetectLanguageWrapper> detectLanguageWrappers =
	new List<simpleT.ST_DetectLanguageWrapper>();

detectLanguageWrappers.add(stDetectLanguageWrapper);

// Call the invocable method and pass the list of wrappers.
List<ST_DetectLanguageResponseWrapper> resultWrappers =
	ST_DetectLanguageInvocable.stDetectLanguages(detectLanguageWrappers);

Flow-based language detection

1. Go to Salesforce Flows.
2. Create a new Flow or modify an existing one.
3. For record-triggered Flows, select Optimize the Flow for Actions and Related Records.
4. Set the Flow to run asynchronously.
5. Add a Flow Action for language detection.
6. In the Action search bar, type Simple Translate Source Language detection.
7. Use Simple Translate Source Language Detection to detect the language of the input text.
8. The action accepts a List<ST_DetectLanguageWrapper> parameter (see the wrapper section below).

ST_DetectLanguageWrapper class

• Encapsulates detected_lan, engine, and texts.
• Required: engine and texts.
• Available engines: ST AWS Default, ST Google Translate Default, ST DeepL Default (plus any custom engines).
• Supported language ISO codes per engine are available in the Simple Translate app.
• detected_lan is a list of ST_DetectLanguageResponseWrapper.Detected_lan items, each with a languageCode and score.

Practical examples

Example 1: Customer support ticket routing

Scenario: Automatically route support tickets based on the customer's language.

Flow setup

• Trigger: When Case is created.
• Variable: ticketText = {!$Record.Description}.
• Language detection:
• Decision logic:
• Update records:

Example 2: Survey response language analysis

Scenario: Group survey responses by language.

• Trigger: Survey Response submitted.
• Variable: responseText = {!$Record.Comments__c}.
• Language detection:
• Actions based on language:
• Update records:

Example 3: Email language identification

Scenario: Identify the language of incoming emails for appropriate auto-responses.

• Trigger: Email-to-Case.
• Variables:
• Language detection:
• Confidence-based actions:

Example 4: Document classification

Scenario: Automatically classify uploaded documents by language.

• Trigger: Document uploaded.
• Variables:
• Language detection:
• Classification logic based on detected language:
• Update records: