dify/api/controllers/web/audio.py
Charlie.Wei fd5c45ae10
Add tts document&fix bug (#2156)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Yeuoly <45712896+Yeuoly@users.noreply.github.com>
2024-01-24 23:04:14 +08:00

103 lines
4.2 KiB
Python

# -*- coding:utf-8 -*-
import logging
import services
from controllers.web import api
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 flask import request
from models.model import App, AppModelConfig
from services.audio_service import AudioService
from services.errors.audio import (AudioTooLargeServiceError, NoAudioUploadedServiceError,
ProviderNotSupportSpeechToTextServiceError, UnsupportedAudioTypeServiceError)
from werkzeug.exceptions import InternalServerError
class AudioApi(WebApiResource):
def post(self, app_model: App, end_user):
app_model_config: AppModelConfig = app_model.app_model_config
if not app_model_config.speech_to_text_dict['enabled']:
raise AppUnavailableError()
file = request.files['file']
try:
response = AudioService.transcript_asr(
tenant_id=app_model.tenant_id,
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(WebApiResource):
def post(self, app_model: App, end_user):
try:
response = AudioService.transcript_tts(
tenant_id=app_model.tenant_id,
text=request.form['text'],
end_user=end_user.external_user_id,
streaming=False
)
return {'data': response.data.decode('latin1')}
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')