Fix tts api err (#6349)

Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>

api/controllers/console/explore/audio.py

@@ -78,10 +78,12 @@ class ChatTextApi(InstalledAppResource):
             parser = reqparse.RequestParser()
             parser.add_argument('message_id', type=str, required=False, location='json')
             parser.add_argument('voice', type=str, location='json')
+            parser.add_argument('text', type=str, location='json')
             parser.add_argument('streaming', type=bool, location='json')
             args = parser.parse_args()
 
-            message_id = args.get('message_id')
+            message_id = args.get('message_id', None)
+            text = args.get('text', None)
             if (app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
                     and app_model.workflow
                     and app_model.workflow.features_dict):
@@ -95,7 +97,8 @@ class ChatTextApi(InstalledAppResource):
             response = AudioService.transcript_tts(
                 app_model=app_model,
                 message_id=message_id,
-                voice=voice
+                voice=voice,
+                text=text
             )
             return response
         except services.errors.app_model_config.AppModelConfigBrokenError:

api/controllers/service_api/app/audio.py

@@ -76,10 +76,12 @@ class TextApi(Resource):
             parser = reqparse.RequestParser()
             parser.add_argument('message_id', type=str, required=False, location='json')
             parser.add_argument('voice', type=str, location='json')
+            parser.add_argument('text', type=str, location='json')
             parser.add_argument('streaming', type=bool, location='json')
             args = parser.parse_args()
 
-            message_id = args.get('message_id')
+            message_id = args.get('message_id', None)
+            text = args.get('text', None)
             if (app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
                     and app_model.workflow
                     and app_model.workflow.features_dict):
@@ -87,15 +89,15 @@ class TextApi(Resource):
                 voice = args.get('voice') if args.get('voice') else text_to_speech.get('voice')
             else:
                 try:
-                    voice = args.get('voice') if args.get('voice') else app_model.app_model_config.text_to_speech_dict.get(
-                        'voice')
+                    voice = args.get('voice') if args.get('voice') else app_model.app_model_config.text_to_speech_dict.get('voice')
                 except Exception:
                     voice = None
             response = AudioService.transcript_tts(
                 app_model=app_model,
                 message_id=message_id,
                 end_user=end_user.external_user_id,
-                voice=voice
+                voice=voice,
+                text=text
             )
 
             return response

api/controllers/web/audio.py

@@ -74,10 +74,12 @@ class TextApi(WebApiResource):
             parser = reqparse.RequestParser()
             parser.add_argument('message_id', type=str, required=False, location='json')
             parser.add_argument('voice', type=str, location='json')
+            parser.add_argument('text', type=str, location='json')
             parser.add_argument('streaming', type=bool, location='json')
             args = parser.parse_args()
 
-            message_id = args.get('message_id')
+            message_id = args.get('message_id', None)
+            text = args.get('text', None)
             if (app_model.mode in [AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value]
                     and app_model.workflow
                     and app_model.workflow.features_dict):
@@ -94,7 +96,8 @@ class TextApi(WebApiResource):
                 app_model=app_model,
                 message_id=message_id,
                 end_user=end_user.external_user_id,
-                voice=voice
+                voice=voice,
+                text=text
             )
 
             return response