File size: 5,214 Bytes
a8b3f00
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
import logging

from flask import request
from flask_restful import Resource, reqparse
from werkzeug.exceptions import InternalServerError

import services
from controllers.service_api import api
from controllers.service_api.app.error import (
    AppUnavailableError,
    AudioTooLargeError,
    CompletionRequestError,
    NoAudioUploadedError,
    ProviderModelCurrentlyNotSupportError,
    ProviderNotInitializeError,
    ProviderNotSupportSpeechToTextError,
    ProviderQuotaExceededError,
    UnsupportedAudioTypeError,
)
from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.model_runtime.errors.invoke import InvokeError
from models.model import App, AppMode, EndUser
from services.audio_service import AudioService
from services.errors.audio import (
    AudioTooLargeServiceError,
    NoAudioUploadedServiceError,
    ProviderNotSupportSpeechToTextServiceError,
    UnsupportedAudioTypeServiceError,
)


class AudioApi(Resource):
    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.FORM))
    def post(self, app_model: App, end_user: EndUser):
        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:
            logging.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:
            logging.exception("internal server error.")
            raise InternalServerError()


class TextApi(Resource):
    @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON))
    def post(self, app_model: App, end_user: EndUser):
        try:
            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", 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
            ):
                text_to_speech = app_model.workflow.features_dict.get("text_to_speech")
                voice = args.get("voice") or text_to_speech.get("voice")
            else:
                try:
                    voice = args.get("voice") or 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, text=text
            )

            return response
        except services.errors.app_model_config.AppModelConfigBrokenError:
            logging.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:
            logging.exception("internal server error.")
            raise InternalServerError()


api.add_resource(AudioApi, "/audio-to-text")
api.add_resource(TextApi, "/text-to-audio")