dify/api/controllers/console/explore/audio.py

import logging

from flask import request
from pydantic import BaseModel, Field
from werkzeug.exceptions import InternalServerError

import services
from controllers.common.schema import register_schema_model
from controllers.console.app.error import (
    AppUnavailableError,
    AudioTooLargeError,
    CompletionRequestError,
    NoAudioUploadedError,
    ProviderModelCurrentlyNotSupportError,
    ProviderNotInitializeError,
    ProviderNotSupportSpeechToTextError,
    ProviderQuotaExceededError,
    UnsupportedAudioTypeError,
)
from controllers.console.explore.wraps import InstalledAppResource
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.model_runtime.errors.invoke import InvokeError
from services.audio_service import AudioService
from services.errors.audio import (
    AudioTooLargeServiceError,
    NoAudioUploadedServiceError,
    ProviderNotSupportSpeechToTextServiceError,
    UnsupportedAudioTypeServiceError,
)

from .. import console_ns

logger = logging.getLogger(__name__)


class TextToAudioPayload(BaseModel):
    message_id: str | None = None
    voice: str | None = None
    text: str | None = None
    streaming: bool | None = Field(default=None, description="Enable streaming response")


register_schema_model(console_ns, TextToAudioPayload)


@console_ns.route(
    "/installed-apps/<uuid:installed_app_id>/audio-to-text",
    endpoint="installed_app_audio",
)
class ChatAudioApi(InstalledAppResource):
    def post(self, installed_app):
        app_model = installed_app.app

        file = request.files["file"]

        try:
            response = AudioService.transcript_asr(app_model=app_model, file=file, end_user=None)

            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("internal server error.")
            raise InternalServerError()


@console_ns.route(
    "/installed-apps/<uuid:installed_app_id>/text-to-audio",
    endpoint="installed_app_text",
)
class ChatTextApi(InstalledAppResource):
    @console_ns.expect(console_ns.models[TextToAudioPayload.__name__])
    def post(self, installed_app):
        app_model = installed_app.app
        try:
            payload = TextToAudioPayload.model_validate(console_ns.payload or {})

            message_id = payload.message_id
            text = payload.text
            voice = payload.voice

            response = AudioService.transcript_tts(app_model=app_model, text=text, voice=voice, 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("internal server error.")
            raise InternalServerError()