diff --git a/apps/setting/models_provider/impl/aliyun_bai_lian_model_provider/model/llm.py b/apps/setting/models_provider/impl/aliyun_bai_lian_model_provider/model/llm.py
index 98f783ce593..6484e649eff 100644
--- a/apps/setting/models_provider/impl/aliyun_bai_lian_model_provider/model/llm.py
+++ b/apps/setting/models_provider/impl/aliyun_bai_lian_model_provider/model/llm.py
@@ -5,7 +5,6 @@
 from setting.models_provider.base_model_provider import MaxKBBaseModel
 from setting.models_provider.impl.base_chat_open_ai import BaseChatOpenAI
 
-
 class BaiLianChatModel(MaxKBBaseModel, BaseChatOpenAI):
     @staticmethod
     def is_cache_model():
@@ -14,6 +13,8 @@ def is_cache_model():
     @staticmethod
     def new_instance(model_type, model_name, model_credential: Dict[str, object], **model_kwargs):
         optional_params = MaxKBBaseModel.filter_optional_params(model_kwargs)
+        if model_name == 'qwen-omni-turbo':
+            optional_params['streaming'] = True
         return BaiLianChatModel(
             model=model_name,
             openai_api_base=model_credential.get('api_base'),
diff --git a/apps/setting/models_provider/impl/aliyun_bai_lian_model_provider/model/stt.py b/apps/setting/models_provider/impl/aliyun_bai_lian_model_provider/model/stt.py
index e21f1637602..ad17a32a95b 100644
--- a/apps/setting/models_provider/impl/aliyun_bai_lian_model_provider/model/stt.py
+++ b/apps/setting/models_provider/impl/aliyun_bai_lian_model_provider/model/stt.py
@@ -26,6 +26,8 @@ def new_instance(model_type, model_name, model_credential: Dict[str, object], **
             optional_params['max_tokens'] = model_kwargs['max_tokens']
         if 'temperature' in model_kwargs and model_kwargs['temperature'] is not None:
             optional_params['temperature'] = model_kwargs['temperature']
+        if model_name == 'qwen-omni-turbo':
+            optional_params['streaming'] = True
         return AliyunBaiLianSpeechToText(
             model=model_name,
             api_key=model_credential.get('api_key'),