>|h,ddlZddlmZddlmZddlmZddlmZddl m Z dd l m Z dd l mZdd lmZdd lmZdd lmZddlmZej,ej.dZGddZGddZy)N)SyncClientWrapper)core)/SpeechToTextConvertRequestTimestampsGranularity)RequestOptions)SpeechToTextChunkResponseModel)construct_type)UnprocessableEntityError)HttpValidationError)JSONDecodeError)ApiError)AsyncClientWrapper.c^eZdZdefdZdeeeeeedddedejde je de jed e je d e je d e je d e je d e je jede jedefdZy)SpeechToTextClientclient_wrapperc||_yN_client_wrapperselfrs _/var/www/html/test/engine/venv/lib/python3.12/site-packages/elevenlabs/speech_to_text/client.py__init__zSpeechToTextClient.__init__ -Nenable_logging language_codetag_audio_events num_speakerstimestamps_granularitydiarizebiased_keywordsrequest_optionsmodel_idfilerrr r!r"r#r$r%returnc b|jjjddd|i||||||| dd|i| t} d| jcxkrdkr:nn7t j ttt| j S| jd k(r@tt j ttt| j | j} t| j| #t$r"t| j| j wxYw) a Transcribe an audio or video file. Parameters ---------- model_id : str The ID of the model to use for transcription, currently only 'scribe_v1' is available. file : core.File See core.File for more documentation enable_logging : typing.Optional[bool] When enable_logging is set to false zero retention mode will be used for the request. This will mean history features are unavailable for this request, including request stitching. Zero retention mode may only be used by enterprise customers. language_code : typing.Optional[str] An ISO-639-1 or ISO-639-3 language_code corresponding to the language of the audio file. Can sometimes improve transcription performance if known beforehand. Defaults to null, in this case the language is predicted automatically. tag_audio_events : typing.Optional[bool] Whether to tag audio events like (laughter), (footsteps), etc. in the transcription. num_speakers : typing.Optional[int] The maximum amount of speakers talking in the uploaded file. Can help with predicting who speaks when. The maximum amount of speakers that can be predicted is 32. Defaults to null, in this case the amount of speakers is set to the maximum value the model supports. timestamps_granularity : typing.Optional[SpeechToTextConvertRequestTimestampsGranularity] The granularity of the timestamps in the transcription. 'word' provides word-level timestamps and 'character' provides character-level timestamps per word. diarize : typing.Optional[bool] Whether to annotate which speaker is currently talking in the uploaded file. biased_keywords : typing.Optional[typing.List[str]] A list of keywords and their biases. The keywords are the words that you want to bias the transcription towards. The biases decide how much the model should boost or suppress the keyword. The biases should be numbers between -10 and 10. The number of keywords cannot exceed 100. The length of each keyword must be less than 50 characters. Each keyword-bias pair must be separated by a colon. For example ["keyword_a:0.42", "keyword_b:-0.5"] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- SpeechToTextChunkResponseModel Successful Response Examples -------- from elevenlabs import ElevenLabs client = ElevenLabs( api_key="YOUR_API_KEY", ) client.speech_to_text.convert( model_id="model_id", ) v1/speech-to-textPOSTrr&rr r!r"r#r$r'methodparamsdatafilesr%omit,type_object_ status_codebodyr httpx_clientrequestOMITr:typingcastr r jsonr r r rtext rr&r'rrr r!r"r#r$r% _response_response_jsons rconvertzSpeechToTextClient.converts6B((55==  .%!.$4 ,*@"#2,'> * Si++1c1{{2"< ) 0$$+.KK+&"5$-NN$4'^^-N9#8#8~NN Sy'<'<9>>R R SsAD AD+D.)__name__ __module__ __qualname__rrr?strrFiler@OptionalboolintrListrr rGrrrrs .*;.15.226-1cg)-=A;?lOlOii lO - lO s+ lO!//$/lOooc*lO!'0_ `lO&lO S)9:lO 8lO (lOrrc^eZdZdefdZdeeeeeedddedejde je de jed e je d e je d e je d e je d e je jede jedefdZy)AsyncSpeechToTextClientrc||_yrrrs rrz AsyncSpeechToTextClient.__init__rrNrr&r'rrr r!r"r#r$r%r(c ~K|jjjddd|i||||||| dd|i| td{} d| jcxkrd kr:nn7t j ttt| j S| jd k(r@tt j ttt| j | j} t| j| 7#t$r"t| j| j wxYww) a; Transcribe an audio or video file. Parameters ---------- model_id : str The ID of the model to use for transcription, currently only 'scribe_v1' is available. file : core.File See core.File for more documentation enable_logging : typing.Optional[bool] When enable_logging is set to false zero retention mode will be used for the request. This will mean history features are unavailable for this request, including request stitching. Zero retention mode may only be used by enterprise customers. language_code : typing.Optional[str] An ISO-639-1 or ISO-639-3 language_code corresponding to the language of the audio file. Can sometimes improve transcription performance if known beforehand. Defaults to null, in this case the language is predicted automatically. tag_audio_events : typing.Optional[bool] Whether to tag audio events like (laughter), (footsteps), etc. in the transcription. num_speakers : typing.Optional[int] The maximum amount of speakers talking in the uploaded file. Can help with predicting who speaks when. The maximum amount of speakers that can be predicted is 32. Defaults to null, in this case the amount of speakers is set to the maximum value the model supports. timestamps_granularity : typing.Optional[SpeechToTextConvertRequestTimestampsGranularity] The granularity of the timestamps in the transcription. 'word' provides word-level timestamps and 'character' provides character-level timestamps per word. diarize : typing.Optional[bool] Whether to annotate which speaker is currently talking in the uploaded file. biased_keywords : typing.Optional[typing.List[str]] A list of keywords and their biases. The keywords are the words that you want to bias the transcription towards. The biases decide how much the model should boost or suppress the keyword. The biases should be numbers between -10 and 10. The number of keywords cannot exceed 100. The length of each keyword must be less than 50 characters. Each keyword-bias pair must be separated by a colon. For example ["keyword_a:0.42", "keyword_b:-0.5"] request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- SpeechToTextChunkResponseModel Successful Response Examples -------- import asyncio from elevenlabs import AsyncElevenLabs client = AsyncElevenLabs( api_key="YOUR_API_KEY", ) async def main() -> None: await client.speech_to_text.convert( model_id="model_id", ) asyncio.run(main()) r*r+rr,r'r-Nr3r4r5r8r9r<rDs rrGzAsyncSpeechToTextClient.convertsFR..;;CC  .%!.$4 ,*@"#2,'D  * Si++1c1{{2"< ) 0$$+.KK+&"5$-NN$4'^^-N9#8#8~NNW R Sy'<'<9>>R R Ss8AD=D D=ADD=AD6D=+D::D=)rHrIrJrrr?rKrrLr@rMrNrOrrPrr rGrQrrrSrSs .*<.15.226-1cg)-=A;?tOtOii tO - tO s+ tO!//$/tOooc*tO!'0_ `tO&tO S)9:tO 8tO (tOrrS)r@core.client_wrapperrr;types.speech_to_text_convert_request_timestamps_granularityrcore.request_optionsr)types.speech_to_text_chunk_response_modelr core.unchecked_base_modelr !errors.unprocessable_entity_errorr types.http_validation_errorr json.decoderr core.api_errorrrrAAnyr?rrSrQrrras`3x1V6H=(%4v{{6::s#pOpOfxOxOr