import logging from flask import request from werkzeug.exceptions import InternalServerError 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 models.model import App from services.audio_service import AudioService from services.errors.audio import ( AudioTooLargeServiceError, NoAudioUploadedServiceError, ProviderNotSupportSpeechToTextServiceError, UnsupportedAudioTypeServiceError, ) class AudioApi(WebApiResource): def post(self, app_model: App, end_user): 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(f"internal server error: {str(e)}") raise InternalServerError() class TextApi(WebApiResource): def post(self, app_model: App, end_user): try: response = AudioService.transcript_tts( app_model=app_model, text=request.form['text'], end_user=end_user.external_user_id, voice=request.form.get('voice'), 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(f"internal server error: {str(e)}") raise InternalServerError() api.add_resource(AudioApi, '/audio-to-text') api.add_resource(TextApi, '/text-to-audio')