feat(stt): add recognize enrichments, add new function detectLanguage

Author: apaparazzi0329

speech-to-text/src/main/java/com/ibm/watson/speech_to_text/v1/SpeechToText.java

@@ -1,5 +1,5 @@
 /*
- * (C) Copyright IBM Corp. 2016, 2025.
+ * (C) Copyright IBM Corp. 2016, 2026.
  *
  * Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
  * the License. You may obtain a copy of the License at
@@ -51,6 +51,7 @@
 import com.ibm.watson.speech_to_text.v1.model.DeleteLanguageModelOptions;
 import com.ibm.watson.speech_to_text.v1.model.DeleteUserDataOptions;
 import com.ibm.watson.speech_to_text.v1.model.DeleteWordOptions;
+import com.ibm.watson.speech_to_text.v1.model.DetectLanguageOptions;
 import com.ibm.watson.speech_to_text.v1.model.GetAcousticModelOptions;
 import com.ibm.watson.speech_to_text.v1.model.GetAudioOptions;
 import com.ibm.watson.speech_to_text.v1.model.GetCorpusOptions;
@@ -60,6 +61,7 @@
 import com.ibm.watson.speech_to_text.v1.model.GetWordOptions;
 import com.ibm.watson.speech_to_text.v1.model.Grammar;
 import com.ibm.watson.speech_to_text.v1.model.Grammars;
+import com.ibm.watson.speech_to_text.v1.model.LanguageDetectionResults;
 import com.ibm.watson.speech_to_text.v1.model.LanguageModel;
 import com.ibm.watson.speech_to_text.v1.model.LanguageModels;
 import com.ibm.watson.speech_to_text.v1.model.ListAcousticModelsOptions;
@@ -447,6 +449,9 @@ public ServiceCall<SpeechRecognitionResults> recognize(RecognizeOptions recogniz
     if (recognizeOptions.speechBeginEvent() != null) {
       builder.query("speech_begin_event", String.valueOf(recognizeOptions.speechBeginEvent()));
     }
+    if (recognizeOptions.enrichments() != null) {
+      builder.query("enrichments", String.valueOf(recognizeOptions.enrichments()));
+    }
     if (recognizeOptions.languageCustomizationId() != null) {
       builder.query(
           "language_customization_id", String.valueOf(recognizeOptions.languageCustomizationId()));
@@ -776,6 +781,12 @@ public ServiceCall<RecognitionJob> createJob(CreateJobOptions createJobOptions)
     if (createJobOptions.resultsTtl() != null) {
       builder.query("results_ttl", String.valueOf(createJobOptions.resultsTtl()));
     }
+    if (createJobOptions.speechBeginEvent() != null) {
+      builder.query("speech_begin_event", String.valueOf(createJobOptions.speechBeginEvent()));
+    }
+    if (createJobOptions.enrichments() != null) {
+      builder.query("enrichments", String.valueOf(createJobOptions.enrichments()));
+    }
     if (createJobOptions.languageCustomizationId() != null) {
       builder.query(
           "language_customization_id", String.valueOf(createJobOptions.languageCustomizationId()));
@@ -2801,4 +2812,43 @@ public ServiceCall<Void> deleteUserData(DeleteUserDataOptions deleteUserDataOpti
     ResponseConverter<Void> responseConverter = ResponseConverterUtils.getVoid();
     return createServiceCall(builder.build(), responseConverter);
   }
+
+  /**
+   * Spoken language identification.
+   *
+   * <p>Detects the spoken language in audio streams. The endpoint is `/v1/detect_language` and user
+   * can optionally include `lid_confidence` parameter to set a custom confidence threshold for
+   * detection. The model continuously processes incoming audio and returns the identified language
+   * when it reaches a confidence level higher than the specified threshold (0.99 by default). See
+   * [Spoken language
+   * identification](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-speech-language-identification).
+   *
+   * @param detectLanguageOptions the {@link DetectLanguageOptions} containing the options for the
+   *     call
+   * @return a {@link ServiceCall} with a result of type {@link LanguageDetectionResults}
+   */
+  public ServiceCall<LanguageDetectionResults> detectLanguage(
+      DetectLanguageOptions detectLanguageOptions) {
+    com.ibm.cloud.sdk.core.util.Validator.notNull(
+        detectLanguageOptions, "detectLanguageOptions cannot be null");
+    RequestBuilder builder =
+        RequestBuilder.post(
+            RequestBuilder.resolveRequestUrl(getServiceUrl(), "/v1/detect_language"));
+    Map<String, String> sdkHeaders =
+        SdkCommon.getSdkHeaders("speech_to_text", "v1", "detectLanguage");
+    for (Entry<String, String> header : sdkHeaders.entrySet()) {
+      builder.header(header.getKey(), header.getValue());
+    }
+    builder.header("Accept", "application/json");
+    if (detectLanguageOptions.contentType() != null) {
+      builder.header("Content-Type", detectLanguageOptions.contentType());
+    }
+    builder.query("lid_confidence", String.valueOf(detectLanguageOptions.lidConfidence()));
+    builder.bodyContent(
+        detectLanguageOptions.contentType(), null, null, detectLanguageOptions.audio());
+    ResponseConverter<LanguageDetectionResults> responseConverter =
+        ResponseConverterUtils.getValue(
+            new com.google.gson.reflect.TypeToken<LanguageDetectionResults>() {}.getType());
+    return createServiceCall(builder.build(), responseConverter);
+  }
 }

speech-to-text/src/main/java/com/ibm/watson/speech_to_text/v1/model/CreateJobOptions.java

@@ -1,5 +1,5 @@
 /*
- * (C) Copyright IBM Corp. 2018, 2025.
+ * (C) Copyright IBM Corp. 2018, 2026.
  *
  * Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
  * the License. You may obtain a copy of the License at
@@ -247,6 +247,8 @@ public interface Events {
   protected String events;
   protected String userToken;
   protected Long resultsTtl;
+  protected Boolean speechBeginEvent;
+  protected String enrichments;
   protected String languageCustomizationId;
   protected String acousticCustomizationId;
   protected String baseModelVersion;
@@ -284,6 +286,8 @@ public static class Builder {
     private String events;
     private String userToken;
     private Long resultsTtl;
+    private Boolean speechBeginEvent;
+    private String enrichments;
     private String languageCustomizationId;
     private String acousticCustomizationId;
     private String baseModelVersion;
@@ -325,6 +329,8 @@ private Builder(CreateJobOptions createJobOptions) {
       this.events = createJobOptions.events;
       this.userToken = createJobOptions.userToken;
       this.resultsTtl = createJobOptions.resultsTtl;
+      this.speechBeginEvent = createJobOptions.speechBeginEvent;
+      this.enrichments = createJobOptions.enrichments;
       this.languageCustomizationId = createJobOptions.languageCustomizationId;
       this.acousticCustomizationId = createJobOptions.acousticCustomizationId;
       this.baseModelVersion = createJobOptions.baseModelVersion;
@@ -467,6 +473,28 @@ public Builder resultsTtl(long resultsTtl) {
       return this;
     }
 
+    /**
+     * Set the speechBeginEvent.
+     *
+     * @param speechBeginEvent the speechBeginEvent
+     * @return the CreateJobOptions builder
+     */
+    public Builder speechBeginEvent(Boolean speechBeginEvent) {
+      this.speechBeginEvent = speechBeginEvent;
+      return this;
+    }
+
+    /**
+     * Set the enrichments.
+     *
+     * @param enrichments the enrichments
+     * @return the CreateJobOptions builder
+     */
+    public Builder enrichments(String enrichments) {
+      this.enrichments = enrichments;
+      return this;
+    }
+
     /**
      * Set the languageCustomizationId.
      *
@@ -788,6 +816,8 @@ protected CreateJobOptions(Builder builder) {
     events = builder.events;
     userToken = builder.userToken;
     resultsTtl = builder.resultsTtl;
+    speechBeginEvent = builder.speechBeginEvent;
+    enrichments = builder.enrichments;
     languageCustomizationId = builder.languageCustomizationId;
     acousticCustomizationId = builder.acousticCustomizationId;
     baseModelVersion = builder.baseModelVersion;
@@ -940,6 +970,41 @@ public Long resultsTtl() {
     return resultsTtl;
   }
 
+  /**
+   * Gets the speechBeginEvent.
+   *
+   * <p>If `true`, the service returns a response object `SpeechActivity` which contains the time
+   * when a speech activity is detected in the stream. This can be used both in standard and low
+   * latency mode. This feature enables client applications to know that some words/speech has been
+   * detected and the service is in the process of decoding. This can be used in lieu of interim
+   * results in standard mode. Use `sad_module: 2` to increase accuracy and performance in detecting
+   * speech boundaries within the audio stream. See [Using speech recognition
+   * parameters](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-service-features#features-parameters).
+   *
+   * @return the speechBeginEvent
+   */
+  public Boolean speechBeginEvent() {
+    return speechBeginEvent;
+  }
+
+  /**
+   * Gets the enrichments.
+   *
+   * <p>Speech transcript enrichment improves readability of raw ASR transcripts by adding
+   * punctuation (periods, commas, question marks, exclamation points) and intelligent
+   * capitalization (sentence beginnings, proper nouns, acronyms, brand names). To enable
+   * enrichment, add the `enrichments=punctuation` parameter to your recognition request. Supported
+   * languages include English (US, UK, Australia, India), French (France, Canada), German, Italian,
+   * Portuguese (Brazil, Portugal), Spanish (Spain, Latin America, Argentina, Chile, Colombia,
+   * Mexico, Peru), and Japanese. See [Speech transcript
+   * enrichment](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-speech-transcript-enrichment).
+   *
+   * @return the enrichments
+   */
+  public String enrichments() {
+    return enrichments;
+  }
+
   /**
    * Gets the languageCustomizationId.
    *

speech-to-text/src/main/java/com/ibm/watson/speech_to_text/v1/model/DetectLanguageOptions.java

@@ -0,0 +1,167 @@
+/*
+ * (C) Copyright IBM Corp. 2026.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+ * an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations under the License.
+ */
+
+package com.ibm.watson.speech_to_text.v1.model;
+
+import com.ibm.cloud.sdk.core.service.model.GenericModel;
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.FileNotFoundException;
+import java.io.InputStream;
+
+/** The detectLanguage options. */
+public class DetectLanguageOptions extends GenericModel {
+
+  protected Float lidConfidence;
+  protected InputStream audio;
+  protected String contentType;
+
+  /** Builder. */
+  public static class Builder {
+    private Float lidConfidence;
+    private InputStream audio;
+    private String contentType;
+
+    /**
+     * Instantiates a new Builder from an existing DetectLanguageOptions instance.
+     *
+     * @param detectLanguageOptions the instance to initialize the Builder with
+     */
+    private Builder(DetectLanguageOptions detectLanguageOptions) {
+      this.lidConfidence = detectLanguageOptions.lidConfidence;
+      this.audio = detectLanguageOptions.audio;
+      this.contentType = detectLanguageOptions.contentType;
+    }
+
+    /** Instantiates a new builder. */
+    public Builder() {}
+
+    /**
+     * Instantiates a new builder with required properties.
+     *
+     * @param lidConfidence the lidConfidence
+     * @param audio the audio
+     */
+    public Builder(Float lidConfidence, InputStream audio) {
+      this.lidConfidence = lidConfidence;
+      this.audio = audio;
+    }
+
+    /**
+     * Builds a DetectLanguageOptions.
+     *
+     * @return the new DetectLanguageOptions instance
+     */
+    public DetectLanguageOptions build() {
+      return new DetectLanguageOptions(this);
+    }
+
+    /**
+     * Set the lidConfidence.
+     *
+     * @param lidConfidence the lidConfidence
+     * @return the DetectLanguageOptions builder
+     */
+    public Builder lidConfidence(Float lidConfidence) {
+      this.lidConfidence = lidConfidence;
+      return this;
+    }
+
+    /**
+     * Set the audio.
+     *
+     * @param audio the audio
+     * @return the DetectLanguageOptions builder
+     */
+    public Builder audio(InputStream audio) {
+      this.audio = audio;
+      return this;
+    }
+
+    /**
+     * Set the contentType.
+     *
+     * @param contentType the contentType
+     * @return the DetectLanguageOptions builder
+     */
+    public Builder contentType(String contentType) {
+      this.contentType = contentType;
+      return this;
+    }
+
+    /**
+     * Set the audio.
+     *
+     * @param audio the audio
+     * @return the DetectLanguageOptions builder
+     * @throws FileNotFoundException if the file could not be found
+     */
+    public Builder audio(File audio) throws FileNotFoundException {
+      this.audio = new FileInputStream(audio);
+      return this;
+    }
+  }
+
+  protected DetectLanguageOptions() {}
+
+  protected DetectLanguageOptions(Builder builder) {
+    com.ibm.cloud.sdk.core.util.Validator.notNull(
+        builder.lidConfidence, "lidConfidence cannot be null");
+    com.ibm.cloud.sdk.core.util.Validator.notNull(builder.audio, "audio cannot be null");
+    lidConfidence = builder.lidConfidence;
+    audio = builder.audio;
+    contentType = builder.contentType;
+  }
+
+  /**
+   * New builder.
+   *
+   * @return a DetectLanguageOptions builder
+   */
+  public Builder newBuilder() {
+    return new Builder(this);
+  }
+
+  /**
+   * Gets the lidConfidence.
+   *
+   * <p>Set a custom confidence threshold for detection.
+   *
+   * @return the lidConfidence
+   */
+  public Float lidConfidence() {
+    return lidConfidence;
+  }
+
+  /**
+   * Gets the audio.
+   *
+   * <p>The audio to transcribe.
+   *
+   * @return the audio
+   */
+  public InputStream audio() {
+    return audio;
+  }
+
+  /**
+   * Gets the contentType.
+   *
+   * <p>The type of the input.
+   *
+   * @return the contentType
+   */
+  public String contentType() {
+    return contentType;
+  }
+}