feat(model/cosyvoice-v3):add language hints to voice clone

Author: songguocola

src/main/java/com/alibaba/dashscope/audio/omni/OmniRealtimeConversation.java

@@ -107,7 +107,7 @@ public void appendAudio(String audioBase64) {
         OmniRealtimeConstants.PROTOCOL_TYPE,
         OmniRealtimeConstants.PROTOCOL_EVENT_TYPE_APPEND_AUDIO);
     append_request.put(OmniRealtimeConstants.PROTOCOL_AUDIO, audioBase64);
-    log.info("append audio with eid: {}, length: {}", event_id, audioBase64.length());
+    log.debug("append audio with eid: {}, length: {}", event_id, audioBase64.length());
     GsonBuilder builder = new GsonBuilder();
     builder.serializeNulls();
     Gson gson = builder.create();

src/main/java/com/alibaba/dashscope/audio/ttsv2/enrollment/VoiceEnrollmentParam.java

@@ -3,9 +3,13 @@
 import com.alibaba.dashscope.base.HalfDuplexServiceParam;
 import com.alibaba.dashscope.exception.InputRequiredException;
 import com.alibaba.dashscope.utils.ApiKeywords;
+import com.alibaba.dashscope.utils.JsonUtils;
+import com.google.gson.JsonArray;
 import com.google.gson.JsonObject;
 import java.nio.ByteBuffer;
 import java.security.InvalidParameterException;
+import java.util.List;
+
 import lombok.Data;
 import lombok.EqualsAndHashCode;
 import lombok.experimental.SuperBuilder;
@@ -19,6 +23,7 @@ public class VoiceEnrollmentParam extends HalfDuplexServiceParam {
   private VoiceEnrollmentOperationType operationType;
   private String url;
   private String voiceId;
+  private List<String> languageHints = null;
 
   private int pageIndex;
   private int pageSize;
@@ -44,6 +49,9 @@ public JsonObject getInput() {
         input.addProperty("target_model", targetModel);
         input.addProperty("prefix", prefix);
         input.addProperty("url", url);
+        if (languageHints != null) {
+          input.add("language_hints", JsonUtils.toJsonArray(languageHints));
+        }
         break;
       case LIST:
         input.addProperty(ApiKeywords.ACTION, operationType.getValue());

src/main/java/com/alibaba/dashscope/audio/ttsv2/enrollment/VoiceEnrollmentService.java

@@ -142,11 +142,12 @@ public Voice createVoice(
     VoiceEnrollmentParam param =
         VoiceEnrollmentParam.builder()
             .operationType(VoiceEnrollmentOperationType.CREATE)
-            .model(this.model)
+            .model(customParam.getModel().isEmpty() ? this.model : customParam.getModel())
             .targetModel(targetModel)
             .prefix(prefix)
             .url(url)
             .apiKey(apikey)
+            .languageHints(customParam.getLanguageHints())
             .headers(customParam.getHeaders())
             .resources(customParam.getResources())
             .parameters(customParam.getParameters())