tts add voice choose (#2391)

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/app/audio.py

@@ -1,7 +1,7 @@
 import logging
 
 from flask import request
-from flask_restful import Resource
+from flask_restful import Resource, reqparse
 from werkzeug.exceptions import InternalServerError
 
 import services
@@ -23,6 +23,7 @@ from controllers.console.wraps import account_initialization_required
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
 from libs.login import login_required
+from models.model import AppModelConfig
 from services.audio_service import AudioService
 from services.errors.audio import (
     AudioTooLargeServiceError,
@@ -45,7 +46,9 @@ class ChatMessageAudioApi(Resource):
         try:
             response = AudioService.transcript_asr(
                 tenant_id=app_model.tenant_id,
-                file=file
+                file=file,
+                end_user=None,
+                promot=app_model.app_model_config.pre_prompt
             )
 
             return response
@@ -71,7 +74,7 @@ class ChatMessageAudioApi(Resource):
         except ValueError as e:
             raise e
         except Exception as e:
-            logging.exception("internal server error.")
+            logging.exception(f"internal server error, {str(e)}.")
             raise InternalServerError()
 
 
@@ -82,10 +85,17 @@ class ChatMessageTextApi(Resource):
     def post(self, app_id):
         app_id = str(app_id)
         app_model = _get_app(app_id, None)
+
+        app_model_config: AppModelConfig = app_model.app_model_config
+
+        if not app_model_config.text_to_speech_dict['enabled']:
+            raise AppUnavailableError()
+
         try:
             response = AudioService.transcript_tts(
                 tenant_id=app_model.tenant_id,
                 text=request.form['text'],
+                voice=app_model.app_model_config.text_to_speech_dict.get('voice'),
                 streaming=False
             )
 
@@ -112,9 +122,54 @@ class ChatMessageTextApi(Resource):
         except ValueError as e:
             raise e
         except Exception as e:
-            logging.exception("internal server error.")
+            logging.exception(f"internal server error, {str(e)}.")
+            raise InternalServerError()
+
+
+class TextModesApi(Resource):
+    def get(self, app_id: str):
+        app_model = _get_app(str(app_id))
+        app_model_config: AppModelConfig = app_model.app_model_config
+
+        if not app_model_config.text_to_speech_dict['enabled']:
+            raise AppUnavailableError()
+
+        try:
+            parser = reqparse.RequestParser()
+            parser.add_argument('language', type=str, required=True, location='args')
+            args = parser.parse_args()
+
+            response = AudioService.transcript_tts_voices(
+                tenant_id=app_model.tenant_id,
+                language=args['language'],
+            )
+
+            return response
+        except services.errors.audio.ProviderNotSupportTextToSpeechLanageServiceError:
+            raise AppUnavailableError("Text to audio voices language parameter loss.")
+        except NoAudioUploadedServiceError:
+            raise NoAudioUploadedError()
+        except AudioTooLargeServiceError as e:
+            raise AudioTooLargeError(str(e))
+        except UnsupportedAudioTypeServiceError:
+            raise UnsupportedAudioTypeError()
+        except ProviderNotSupportSpeechToTextServiceError:
+            raise ProviderNotSupportSpeechToTextError()
+        except ProviderTokenNotInitError as ex:
+            raise ProviderNotInitializeError(ex.description)
+        except QuotaExceededError:
+            raise ProviderQuotaExceededError()
+        except ModelCurrentlyNotSupportError:
+            raise ProviderModelCurrentlyNotSupportError()
+        except InvokeError as e:
+            raise CompletionRequestError(e.description)
+        except ValueError as e:
+            raise e
+        except Exception as e:
+            logging.exception(f"internal server error, {str(e)}.")
             raise InternalServerError()
 
 
 api.add_resource(ChatMessageAudioApi, '/apps/<uuid:app_id>/audio-to-text')
 api.add_resource(ChatMessageTextApi, '/apps/<uuid:app_id>/text-to-audio')
+api.add_resource(TextModesApi, '/apps/<uuid:app_id>/text-to-audio/voices')