dify

2025-12-01 17:21:38 +08:00
parent 32fee2b8ab
commit fab8c13cb3
7511 changed files with 996300 additions and 0 deletions
--- a/dify/api/controllers/web/audio.py
+++ b/dify/api/controllers/web/audio.py
@@ -0,0 +1,145 @@
+import logging
+
+from flask import request
+from flask_restx import fields, marshal_with, reqparse
+from werkzeug.exceptions import InternalServerError
+
+import services
+from controllers.web import web_ns
+from controllers.web.error import (
+    AppUnavailableError,
+    AudioTooLargeError,
+    CompletionRequestError,
+    NoAudioUploadedError,
+    ProviderModelCurrentlyNotSupportError,
+    ProviderNotInitializeError,
+    ProviderNotSupportSpeechToTextError,
+    ProviderQuotaExceededError,
+    UnsupportedAudioTypeError,
+)
+from controllers.web.wraps import WebApiResource
+from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
+from core.model_runtime.errors.invoke import InvokeError
+from models.model import App
+from services.audio_service import AudioService
+from services.errors.audio import (
+    AudioTooLargeServiceError,
+    NoAudioUploadedServiceError,
+    ProviderNotSupportSpeechToTextServiceError,
+    UnsupportedAudioTypeServiceError,
+)
+
+logger = logging.getLogger(__name__)
+
+
+@web_ns.route("/audio-to-text")
+class AudioApi(WebApiResource):
+    audio_to_text_response_fields = {
+        "text": fields.String,
+    }
+
+    @marshal_with(audio_to_text_response_fields)
+    @web_ns.doc("Audio to Text")
+    @web_ns.doc(description="Convert audio file to text using speech-to-text service.")
+    @web_ns.doc(
+        responses={
+            200: "Success",
+            400: "Bad Request",
+            401: "Unauthorized",
+            403: "Forbidden",
+            413: "Audio file too large",
+            415: "Unsupported audio type",
+            500: "Internal Server Error",
+        }
+    )
+    def post(self, app_model: App, end_user):
+        """Convert audio to text"""
+        file = request.files["file"]
+
+        try:
+            response = AudioService.transcript_asr(app_model=app_model, file=file, end_user=end_user)
+
+            return response
+        except services.errors.app_model_config.AppModelConfigBrokenError:
+            logger.exception("App model config broken.")
+            raise AppUnavailableError()
+        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:
+            logger.exception("Failed to handle post request to AudioApi")
+            raise InternalServerError()
+
+
+@web_ns.route("/text-to-audio")
+class TextApi(WebApiResource):
+    @web_ns.doc("Text to Audio")
+    @web_ns.doc(description="Convert text to audio using text-to-speech service.")
+    @web_ns.doc(
+        responses={
+            200: "Success",
+            400: "Bad Request",
+            401: "Unauthorized",
+            403: "Forbidden",
+            500: "Internal Server Error",
+        }
+    )
+    def post(self, app_model: App, end_user):
+        """Convert text to audio"""
+        try:
+            parser = (
+                reqparse.RequestParser()
+                .add_argument("message_id", type=str, required=False, location="json")
+                .add_argument("voice", type=str, location="json")
+                .add_argument("text", type=str, location="json")
+                .add_argument("streaming", type=bool, location="json")
+            )
+            args = parser.parse_args()
+
+            message_id = args.get("message_id", None)
+            text = args.get("text", None)
+            voice = args.get("voice", None)
+            response = AudioService.transcript_tts(
+                app_model=app_model, text=text, voice=voice, end_user=end_user.external_user_id, message_id=message_id
+            )
+
+            return response
+        except services.errors.app_model_config.AppModelConfigBrokenError:
+            logger.exception("App model config broken.")
+            raise AppUnavailableError()
+        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:
+            logger.exception("Failed to handle post request to TextApi")
+            raise InternalServerError()