chore(hand edits): apply text to speech hand edits

Author: jeff-arn

text-to-speech/src/main/java/com/ibm/watson/text_to_speech/v1/TextToSpeech.java

@@ -62,11 +62,17 @@
 import com.ibm.watson.text_to_speech.v1.model.Voice;
 import com.ibm.watson.text_to_speech.v1.model.Voices;
 import com.ibm.watson.text_to_speech.v1.model.Words;
+import com.ibm.watson.text_to_speech.v1.websocket.SynthesizeCallback;
+import com.ibm.watson.text_to_speech.v1.websocket.TextToSpeechWebSocketListener;
 import java.io.InputStream;
 import java.util.HashMap;
 import java.util.Map;
 import java.util.Map.Entry;
+import okhttp3.HttpUrl;
 import okhttp3.MultipartBody;
+import okhttp3.OkHttpClient;
+import okhttp3.Request;
+import okhttp3.WebSocket;
 
 /**
  * The IBM Watson™ Text to Speech service provides APIs that use IBM's speech-synthesis
@@ -154,6 +160,53 @@ public TextToSpeech(String serviceName, Authenticator authenticator) {
     this.configureService(serviceName);
   }
 
+  /**
+   * Synthesize audio.
+   *
+   * <p>Synthesizes text to audio that is spoken in the specified voice. The service bases its
+   * understanding of the language for the input text on the specified voice. Use a voice that
+   * matches the language of the input text.
+   *
+   * <p>The method accepts a maximum of 5 KB of input text in the body of the request, and 8 KB for
+   * the URL and headers. The 5 KB limit includes any SSML tags that you specify. The service
+   * returns the synthesized audio stream as an array of bytes.
+   *
+   * <p>### Audio formats (accept types)
+   *
+   * <p>For more information about specifying an audio format, including additional details about
+   * some of the formats, see [Audio
+   * formats](https://cloud.ibm.com/docs/text-to-speech?topic=text-to-speech-audioFormats#audioFormats).
+   *
+   * @param synthesizeOptions the {@link SynthesizeOptions} containing the options for the call
+   * @param callback the {@link SynthesizeCallback} callback
+   * @return a {@link WebSocket} instance
+   */
+  public WebSocket synthesizeUsingWebSocket(
+      SynthesizeOptions synthesizeOptions, SynthesizeCallback callback) {
+    com.ibm.cloud.sdk.core.util.Validator.notNull(
+        synthesizeOptions, "synthesizeOptions cannot be null");
+    com.ibm.cloud.sdk.core.util.Validator.notNull(callback, "callback cannot be null");
+
+    HttpUrl.Builder urlBuilder = HttpUrl.parse(getServiceUrl() + "/v1/synthesize").newBuilder();
+
+    if (synthesizeOptions.voice() != null) {
+      urlBuilder.addQueryParameter("voice", synthesizeOptions.voice());
+    }
+    if (synthesizeOptions.customizationId() != null) {
+      urlBuilder.addQueryParameter("customization_id", synthesizeOptions.customizationId());
+    }
+
+    String url = urlBuilder.toString().replace("https://", "wss://");
+    Request.Builder builder = new Request.Builder().url(url);
+
+    setAuthentication(builder);
+    setDefaultHeaders(builder);
+
+    OkHttpClient client = configureHttpClient();
+    return client.newWebSocket(
+        builder.build(), new TextToSpeechWebSocketListener(synthesizeOptions, callback));
+  }
+
   /**
    * List voices.
    *

text-to-speech/src/main/java/com/ibm/watson/text_to_speech/v1/model/SynthesizeOptions.java

@@ -13,6 +13,7 @@
 package com.ibm.watson.text_to_speech.v1.model;
 
 import com.ibm.cloud.sdk.core.service.model.GenericModel;
+import java.util.List;
 
 /** The synthesize options. */
 public class SynthesizeOptions extends GenericModel {
@@ -157,6 +158,7 @@ public interface SpellOutMode {
   protected String spellOutMode;
   protected Long ratePercentage;
   protected Long pitchPercentage;
+  protected List<String> timings;
 
   /** Builder. */
   public static class Builder {
@@ -167,6 +169,7 @@ public static class Builder {
     private String spellOutMode;
     private Long ratePercentage;
     private Long pitchPercentage;
+    private List<String> timings;
 
     /**
      * Instantiates a new Builder from an existing SynthesizeOptions instance.
@@ -181,6 +184,7 @@ private Builder(SynthesizeOptions synthesizeOptions) {
       this.spellOutMode = synthesizeOptions.spellOutMode;
       this.ratePercentage = synthesizeOptions.ratePercentage;
       this.pitchPercentage = synthesizeOptions.pitchPercentage;
+      this.timings = synthesizeOptions.timings;
     }
 
     /** Instantiates a new builder. */
@@ -280,6 +284,17 @@ public Builder pitchPercentage(long pitchPercentage) {
       this.pitchPercentage = pitchPercentage;
       return this;
     }
+
+    /**
+     * Set the timings.
+     *
+     * @param timings the list of timings
+     * @return the SynthesizeOptions builder
+     */
+    public Builder timings(List<String> timings) {
+      this.timings = timings;
+      return this;
+    }
   }
 
   protected SynthesizeOptions() {}
@@ -429,4 +444,21 @@ public Long ratePercentage() {
   public Long pitchPercentage() {
     return pitchPercentage;
   }
+
+  /**
+   * Gets the timings.
+   *
+   * <p>An array that specifies whether the service is to return word timing information for all
+   * strings of the input text. Specify `words` as the element of the array to request word timing
+   * information. The service returns the start and end time of each word of the input. Specify an
+   * empty array or omit the parameter to receive no word timing information. Not supported for
+   * Japanese input text.
+   *
+   * <p>NOTE: This parameter only works for the `synthesizeUsingWebSocket` method.
+   *
+   * @return the timings
+   */
+  public List<String> timings() {
+    return timings;
+  }
 }