>|h/?ZddlZddlmZddlmZddlmZddlmZddl m Z dd l m Z dd l mZdd lmZdd lmZdd lmZddlmZddlmZddlmZddlmZddlmZddlm Z ddl!m"Z"ddl#m$Z$ddl%Z%ddlm&Z&ejNejPdZ)GddZ*GddZ+y)N)SyncClientWrapper) OutputFormat) VoiceSettings)%PronunciationDictionaryVersionLocator)?BodyTextToSpeechV1TextToSpeechVoiceIdPostApplyTextNormalization)RequestOptions)jsonable_encoder)'convert_and_respect_annotation_metadata)UnprocessableEntityError)HttpValidationError)construct_type)JSONDecodeError)ApiError)[BodyTextToSpeechWithTimestampsV1TextToSpeechVoiceIdWithTimestampsPostApplyTextNormalization) AudioWithTimestampsResponseModel)NBodyTextToSpeechStreamingV1TextToSpeechVoiceIdStreamPostApplyTextNormalization)jBodyTextToSpeechStreamingWithTimestampsV1TextToSpeechVoiceIdStreamWithTimestampsPostApplyTextNormalization).StreamingAudioChunkWithTimestampsResponseModel)AsyncClientWrapper.c&~ eZdZdefdZdddeeeeeeeeeeedddededeje deje d eje d ejed ejed eje d ejejedeje dejedejedejejedejejedeje dejedejedej"ef$dZdddeeeeeeeeeeedddededeje deje d eje d ejed ejed eje d ejejedeje dejedejedejejedejejedeje dejedejedef$dZdddeeeeeeeeeeedddededeje deje d eje d ejed ejed eje d ejejedeje dejedejedejejedejejedeje dejedejedej"ef$dZdddeeeeeeeeeeedddededeje deje d eje d ejed ejed eje d ejejedeje dejedejedejejedejejedeje dejedejedej"ef$dZy)TextToSpeechClientclient_wrapperc||_yN_client_wrapperselfrs _/var/www/html/test/engine/venv/lib/python3.12/site-packages/elevenlabs/text_to_speech/client.py__init__zTextToSpeechClient.__init__& -Nenable_loggingoptimize_streaming_latency output_formatmodel_id language_codevoice_settings!pronunciation_dictionary_locatorsseed previous_text next_textprevious_request_idsnext_request_idsuse_pvc_as_ivcapply_text_normalizationrequest_optionsvoice_idtextr&r'r(r)r*r+r,r-r.r/r0r1r2r3r4returnc#4K|jjjdt|d|||d|||t |t dt | t jtd| | | | |||d ddi|t 5} d |jcxkrd kr>nn;||jd dnd}|j|D]}| d d d y |j|jdk(r@tt jt t#t |j%|j%}t)|j|#t&$r"t)|j|j*wxYw#1swYy xYww)a Converts text into speech using a voice of your choice and returns audio. Parameters ---------- voice_id : str Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices. text : str The text that will get converted into speech. 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. optimize_streaming_latency : typing.Optional[int] You can turn on latency optimizations at some cost of quality. The best possible final latency varies by model. Possible values: 0 - default mode (no latency optimizations) 1 - normal latency optimizations (about 50% of possible latency improvement of option 3) 2 - strong latency optimizations (about 75% of possible latency improvement of option 3) 3 - max latency optimizations 4 - max latency optimizations, but also with text normalizer turned off for even more latency savings (best latency, but can mispronounce eg numbers and dates). Defaults to None. output_format : typing.Optional[OutputFormat] The output format of the generated audio. model_id : typing.Optional[str] Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property. language_code : typing.Optional[str] Language code (ISO 639-1) used to enforce a language for the model. Currently only Turbo v2.5 and Flash v2.5 support language enforcement. For other models, an error will be returned if language code is provided. voice_settings : typing.Optional[VoiceSettings] Voice settings overriding stored settings for the given voice. They are applied only on the given request. pronunciation_dictionary_locators : typing.Optional[typing.Sequence[PronunciationDictionaryVersionLocator]] A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request seed : typing.Optional[int] If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295. previous_text : typing.Optional[str] The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. next_text : typing.Optional[str] The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. previous_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that were generated before this generation. Can be used to improve the speech's continuity when splitting up a large task into multiple requests. The results will be best when the same model is used across the generations. In case both previous_text and previous_request_ids is send, previous_text will be ignored. A maximum of 3 request_ids can be send. next_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that come after this generation. next_request_ids is especially useful for maintaining the speech's continuity when regenerating a sample that has had some audio quality issues. For example, if you have generated 3 speech clips, and you want to improve clip 2, passing the request id of clip 3 as a next_request_id (and that of clip 1 as a previous_request_id) will help maintain natural flow in the combined speech. The results will be best when the same model is used across the generations. In case both next_text and next_request_ids is send, next_text will be ignored. A maximum of 3 request_ids can be send. use_pvc_as_ivc : typing.Optional[bool] If true, we won't use PVC version of the voice for the generation but the IVC version. This is a temporary workaround for higher latency in PVC versions. apply_text_normalization : typing.Optional[BodyTextToSpeechV1TextToSpeechVoiceIdPostApplyTextNormalization] This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. Cannot be turned on for 'eleven_turbo_v2_5' model. request_options : typing.Optional[RequestOptions] Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response. Yields ------ typing.Iterator[bytes] The generated audio file Examples -------- from elevenlabs import ElevenLabs client = ElevenLabs( api_key="YOUR_API_KEY", ) client.text_to_speech.convert( voice_id="JBFqnCBsd6RMkjVDRZzb", output_format="mp3_44100_128", text="The first move is what sets everything in motion.", model_id="eleven_multilingual_v2", ) v1/text-to-speech/POSTr&r'r(writeobject_ annotation direction r6r)r*r+r,r-r.r/r0r1r2r3 content-typeapplication/jsonmethodparamsjsonheadersr4omit,N chunk_sizerLtype_r> status_codebodyr httpx_clientstreamr r rtypingSequencerOMITrSget iter_bytesreadr castrrrGrrr6r r5r6r&r'r(r)r*r+r,r-r.r/r0r1r2r3r4 _response _chunk_size_chunk_response_jsons r!convertzTextToSpeechClient.convert)sV ! ! . . 5 5 !1(!; < ="0.H!. $!."I*}PW#6]=%/TU%6 !.&(<$4"0,D%* 2,A6! 6 SB W)//5#5M\Mh/"5"5lD"InrK"+"6"6+"6"N%$ %O6 S6 SP ((C/2 /*&9(1(8"+!1y'<'<>R R# W9+@+@y~~VV Wi6 S6 Ss>BFF A E FA/EF +F  F  FFc|jjjdt|dd|||d|||t |t dt | t jtd| | | | |||d dd i|t } d |jcxkrd kr:nn7t jttt|j S|jdk(r@tt jt tt |j |j}t%|j|#t"$r"t%|j|j&wxYw)a Generate speech from text with precise character-level timing information for audio-text synchronization. Parameters ---------- voice_id : str Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices. text : str The text that will get converted into speech. 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. optimize_streaming_latency : typing.Optional[int] You can turn on latency optimizations at some cost of quality. The best possible final latency varies by model. Possible values: 0 - default mode (no latency optimizations) 1 - normal latency optimizations (about 50% of possible latency improvement of option 3) 2 - strong latency optimizations (about 75% of possible latency improvement of option 3) 3 - max latency optimizations 4 - max latency optimizations, but also with text normalizer turned off for even more latency savings (best latency, but can mispronounce eg numbers and dates). Defaults to None. output_format : typing.Optional[OutputFormat] The output format of the generated audio. model_id : typing.Optional[str] Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property. language_code : typing.Optional[str] Language code (ISO 639-1) used to enforce a language for the model. Currently only Turbo v2.5 and Flash v2.5 support language enforcement. For other models, an error will be returned if language code is provided. voice_settings : typing.Optional[VoiceSettings] Voice settings overriding stored settings for the given voice. They are applied only on the given request. pronunciation_dictionary_locators : typing.Optional[typing.Sequence[PronunciationDictionaryVersionLocator]] A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request seed : typing.Optional[int] If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295. previous_text : typing.Optional[str] The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. next_text : typing.Optional[str] The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. previous_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that were generated before this generation. Can be used to improve the speech's continuity when splitting up a large task into multiple requests. The results will be best when the same model is used across the generations. In case both previous_text and previous_request_ids is send, previous_text will be ignored. A maximum of 3 request_ids can be send. next_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that come after this generation. next_request_ids is especially useful for maintaining the speech's continuity when regenerating a sample that has had some audio quality issues. For example, if you have generated 3 speech clips, and you want to improve clip 2, passing the request id of clip 3 as a next_request_id (and that of clip 1 as a previous_request_id) will help maintain natural flow in the combined speech. The results will be best when the same model is used across the generations. In case both next_text and next_request_ids is send, next_text will be ignored. A maximum of 3 request_ids can be send. use_pvc_as_ivc : typing.Optional[bool] If true, we won't use PVC version of the voice for the generation but the IVC version. This is a temporary workaround for higher latency in PVC versions. apply_text_normalization : typing.Optional[BodyTextToSpeechWithTimestampsV1TextToSpeechVoiceIdWithTimestampsPostApplyTextNormalization] This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. Cannot be turned on for 'eleven_turbo_v2_5' model. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AudioWithTimestampsResponseModel Successful Response Examples -------- from elevenlabs import ElevenLabs client = ElevenLabs( api_key="YOUR_API_KEY", ) client.text_to_speech.convert_with_timestamps( voice_id="21m00Tcm4TlvDq8ikWAM", text="This is a test for the API of ElevenLabs.", ) r9/with-timestampsr:r;r<r=rArBrCrDrJrKrPrOrRrrVrequestr r rrXrYrrZrSr^rrrGr rrrr6r r5r6r&r'r(r)r*r+r,r-r.r/r0r1r2r3r4r`rcs r!convert_with_timestampsz*TextToSpeechClient.convert_with_timestampssR((55== !1(!; <! D Si++1c1{{4"> ) 0$$+.KK+&"5$-NN$4'^^-N9#8#8~NN Sy'<'<9>>R R SsAEAE+E3c#6K|jjjdt|dd|||d|||t |t dt | t jtd| | | | |||d dd i|t 5} d |jcxkrd kr>nn;||jddnd}|j|D]}| d d d y |j|jdk(r@tt jt t#t |j%|j%}t)|j|#t&$r"t)|j|j*wxYw#1swYy xYww)a7 Converts text into speech using a voice of your choice and returns audio as an audio stream. Parameters ---------- voice_id : str Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices. text : str The text that will get converted into speech. 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. optimize_streaming_latency : typing.Optional[int] You can turn on latency optimizations at some cost of quality. The best possible final latency varies by model. Possible values: 0 - default mode (no latency optimizations) 1 - normal latency optimizations (about 50% of possible latency improvement of option 3) 2 - strong latency optimizations (about 75% of possible latency improvement of option 3) 3 - max latency optimizations 4 - max latency optimizations, but also with text normalizer turned off for even more latency savings (best latency, but can mispronounce eg numbers and dates). Defaults to None. output_format : typing.Optional[OutputFormat] The output format of the generated audio. model_id : typing.Optional[str] Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property. language_code : typing.Optional[str] Language code (ISO 639-1) used to enforce a language for the model. Currently only Turbo v2.5 and Flash v2.5 support language enforcement. For other models, an error will be returned if language code is provided. voice_settings : typing.Optional[VoiceSettings] Voice settings overriding stored settings for the given voice. They are applied only on the given request. pronunciation_dictionary_locators : typing.Optional[typing.Sequence[PronunciationDictionaryVersionLocator]] A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request seed : typing.Optional[int] If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295. previous_text : typing.Optional[str] The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. next_text : typing.Optional[str] The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. previous_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that were generated before this generation. Can be used to improve the speech's continuity when splitting up a large task into multiple requests. The results will be best when the same model is used across the generations. In case both previous_text and previous_request_ids is send, previous_text will be ignored. A maximum of 3 request_ids can be send. next_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that come after this generation. next_request_ids is especially useful for maintaining the speech's continuity when regenerating a sample that has had some audio quality issues. For example, if you have generated 3 speech clips, and you want to improve clip 2, passing the request id of clip 3 as a next_request_id (and that of clip 1 as a previous_request_id) will help maintain natural flow in the combined speech. The results will be best when the same model is used across the generations. In case both next_text and next_request_ids is send, next_text will be ignored. A maximum of 3 request_ids can be send. use_pvc_as_ivc : typing.Optional[bool] If true, we won't use PVC version of the voice for the generation but the IVC version. This is a temporary workaround for higher latency in PVC versions. apply_text_normalization : typing.Optional[BodyTextToSpeechStreamingV1TextToSpeechVoiceIdStreamPostApplyTextNormalization] This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. Cannot be turned on for 'eleven_turbo_v2_5' model. request_options : typing.Optional[RequestOptions] Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response. Yields ------ typing.Iterator[bytes] Streaming audio data Examples -------- from elevenlabs import ElevenLabs client = ElevenLabs( api_key="YOUR_API_KEY", ) client.text_to_speech.convert_as_stream( voice_id="JBFqnCBsd6RMkjVDRZzb", output_format="mp3_44100_128", text="The first move is what sets everything in motion.", model_id="eleven_multilingual_v2", ) r9/streamr:r;r<r=rArBrCrDrJrKNrLrMrNrOrPrRrUr_s r!convert_as_streamz$TextToSpeechClient.convert_as_streamosV ! ! . . 5 5 !1(!; R R# W9+@+@y~~VV Wi6 S6 Ss>BFF A E FA/EF +F  F  FFc#K|jjjdt|dd|||d|||t |t dt | t jtd| | | | |||d dd i|t 5} d |jcxkrd krpnnm|jD]P} t|d k(rt jtttt!j"|R dddy|j%|jdk(r@t't jt(tt(|j!|j!}t-|j|#YxYw#t*$r"t-|j|j.wxYw#1swYyxYww)a Converts text into speech using a voice of your choice and returns a stream of JSONs containing audio as a base64 encoded string together with information on when which character was spoken. Parameters ---------- voice_id : str Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices. text : str The text that will get converted into speech. 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. optimize_streaming_latency : typing.Optional[int] You can turn on latency optimizations at some cost of quality. The best possible final latency varies by model. Possible values: 0 - default mode (no latency optimizations) 1 - normal latency optimizations (about 50% of possible latency improvement of option 3) 2 - strong latency optimizations (about 75% of possible latency improvement of option 3) 3 - max latency optimizations 4 - max latency optimizations, but also with text normalizer turned off for even more latency savings (best latency, but can mispronounce eg numbers and dates). Defaults to None. output_format : typing.Optional[OutputFormat] The output format of the generated audio. model_id : typing.Optional[str] Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property. language_code : typing.Optional[str] Language code (ISO 639-1) used to enforce a language for the model. Currently only Turbo v2.5 and Flash v2.5 support language enforcement. For other models, an error will be returned if language code is provided. voice_settings : typing.Optional[VoiceSettings] Voice settings overriding stored settings for the given voice. They are applied only on the given request. pronunciation_dictionary_locators : typing.Optional[typing.Sequence[PronunciationDictionaryVersionLocator]] A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request seed : typing.Optional[int] If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295. previous_text : typing.Optional[str] The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. next_text : typing.Optional[str] The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. previous_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that were generated before this generation. Can be used to improve the speech's continuity when splitting up a large task into multiple requests. The results will be best when the same model is used across the generations. In case both previous_text and previous_request_ids is send, previous_text will be ignored. A maximum of 3 request_ids can be send. next_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that come after this generation. next_request_ids is especially useful for maintaining the speech's continuity when regenerating a sample that has had some audio quality issues. For example, if you have generated 3 speech clips, and you want to improve clip 2, passing the request id of clip 3 as a next_request_id (and that of clip 1 as a previous_request_id) will help maintain natural flow in the combined speech. The results will be best when the same model is used across the generations. In case both next_text and next_request_ids is send, next_text will be ignored. A maximum of 3 request_ids can be send. use_pvc_as_ivc : typing.Optional[bool] If true, we won't use PVC version of the voice for the generation but the IVC version. This is a temporary workaround for higher latency in PVC versions. apply_text_normalization : typing.Optional[BodyTextToSpeechStreamingWithTimestampsV1TextToSpeechVoiceIdStreamWithTimestampsPostApplyTextNormalization] This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. Cannot be turned on for 'eleven_turbo_v2_5' model. request_options : typing.Optional[RequestOptions] Request-specific configuration. Yields ------ typing.Iterator[StreamingAudioChunkWithTimestampsResponseModel] Stream of JSON objects containing audio chunks and character timing information Examples -------- from elevenlabs import ElevenLabs client = ElevenLabs( api_key="YOUR_API_KEY", ) response = client.text_to_speech.stream_with_timestamps( voice_id="JBFqnCBsd6RMkjVDRZzb", output_format="mp3_44100_128", text="The first move is what sets everything in motion.", model_id="eleven_multilingual_v2", ) for chunk in response: yield chunk r9/stream/with-timestampsr:r;r<r=rArBrCrDrJrKrrPNrOrR)rrVrWr r rrXrYrrZrS iter_lineslenr^rrrGloadsr]r rrrr6r r5r6r&r'r(r)r*r+r,r-r.r/r0r1r2r3r4r`_textrcs r!stream_with_timestampsz)TextToSpeechClient.stream_with_timestampssZ ! ! . . 5 5 !1(!; <R R#! # W9+@+@y~~VV W}@ S@ SsaBGG+F2FF>F?F G A/F:GFF+GGG G)__name__ __module__ __qualname__rr"rZstrrXOptionalboolintrrrYrr r Iteratorbytesrdrrrjrrmrrrur$r!rr%s.*;.15;?7;)-.29= %).2*.FJBF04 ;?/aSaS aS - aS %+OOC$8 aS|4aS//#&aSs+aS 6aS,2?? OOA B, aSooc"aSs+aS ??3'!aS"%oofooc.BC#aS$!//&//#*>?%aS&-'aS(#)// K# )aS. 8/aS0  1aSP15;?7;)-.29= %).2*.FJBF04 ;?/aOaO aO - aO %+OOC$8 aO|4aO//#&aOs+aO 6aO,2?? OOA B, aOooc"aOs+aO ??3'!aO"%oofooc.BC#aO$!//&//#*>?%aO&-'aO(#)// g# )aO. 8/aO0 *1aOP15;?7;)-.29= %).2*.FJBF04 ;?/aSaS aS - aS %+OOC$8 aS|4aS//#&aSs+aS 6aS,2?? OOA B, aSooc"aSs+aS ??3'!aS"%oofooc.BC#aS$!//&//#*>?%aS&-'aS(#)// Z# )aS. 8/aS0  1aSP15;?7;)-.29= %).2*.FJBF04 ;?/mSmS mS - mS %+OOC$8 mS|4mS//#&mSs+mS 6mS,2?? OOA B, mSooc"mSs+mS ??3'!mS"%oofooc.BC#mS$!//&//#*>?%mS&-'mS(#)// v# )mS. 8/mS0 G H1mSr$rc&~ eZdZdefdZdddeeeeeeeeeeedddededeje deje d eje d ejed ejed eje d ejejedeje dejedejedejejedejejedeje dejedejedej"ef$dZdddeeeeeeeeeeedddededeje deje d eje d ejed ejed eje d ejejedeje dejedejedejejedejejedeje dejedejedef$dZdddeeeeeeeeeeedddededeje deje d eje d ejed ejed eje d ejejedeje dejedejedejejedejejedeje dejedejedej"ef$dZdddeeeeeeeeeeedddededeje deje d eje d ejed ejed eje d ejejedeje dejedejedejejedejejedeje dejedejedej"ef$dZy)AsyncTextToSpeechClientrc||_yrrrs r!r"z AsyncTextToSpeechClient.__init__r#r$Nr%r5r6r&r'r(r)r*r+r,r-r.r/r0r1r2r3r4r7cK|jjjdt|d|||d|||t |t dt | t jtd| | | | |||d ddi|t 4d {} d |jcxkrd kr:nn7||jd dnd}|j|23d {}||jd {|jdk(r@tt jt t#t |j%|j%}t)|j|776 d d d d {7y 7#t&$r"t)|j|j*wxYw#1d {7swYy xYww)a Converts text into speech using a voice of your choice and returns audio. Parameters ---------- voice_id : str Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices. text : str The text that will get converted into speech. 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. optimize_streaming_latency : typing.Optional[int] You can turn on latency optimizations at some cost of quality. The best possible final latency varies by model. Possible values: 0 - default mode (no latency optimizations) 1 - normal latency optimizations (about 50% of possible latency improvement of option 3) 2 - strong latency optimizations (about 75% of possible latency improvement of option 3) 3 - max latency optimizations 4 - max latency optimizations, but also with text normalizer turned off for even more latency savings (best latency, but can mispronounce eg numbers and dates). Defaults to None. output_format : typing.Optional[OutputFormat] The output format of the generated audio. model_id : typing.Optional[str] Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property. language_code : typing.Optional[str] Language code (ISO 639-1) used to enforce a language for the model. Currently only Turbo v2.5 and Flash v2.5 support language enforcement. For other models, an error will be returned if language code is provided. voice_settings : typing.Optional[VoiceSettings] Voice settings overriding stored settings for the given voice. They are applied only on the given request. pronunciation_dictionary_locators : typing.Optional[typing.Sequence[PronunciationDictionaryVersionLocator]] A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request seed : typing.Optional[int] If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295. previous_text : typing.Optional[str] The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. next_text : typing.Optional[str] The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. previous_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that were generated before this generation. Can be used to improve the speech's continuity when splitting up a large task into multiple requests. The results will be best when the same model is used across the generations. In case both previous_text and previous_request_ids is send, previous_text will be ignored. A maximum of 3 request_ids can be send. next_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that come after this generation. next_request_ids is especially useful for maintaining the speech's continuity when regenerating a sample that has had some audio quality issues. For example, if you have generated 3 speech clips, and you want to improve clip 2, passing the request id of clip 3 as a next_request_id (and that of clip 1 as a previous_request_id) will help maintain natural flow in the combined speech. The results will be best when the same model is used across the generations. In case both next_text and next_request_ids is send, next_text will be ignored. A maximum of 3 request_ids can be send. use_pvc_as_ivc : typing.Optional[bool] If true, we won't use PVC version of the voice for the generation but the IVC version. This is a temporary workaround for higher latency in PVC versions. apply_text_normalization : typing.Optional[BodyTextToSpeechV1TextToSpeechVoiceIdPostApplyTextNormalization] This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. Cannot be turned on for 'eleven_turbo_v2_5' model. request_options : typing.Optional[RequestOptions] Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response. Yields ------ typing.AsyncIterator[bytes] The generated audio file Examples -------- import asyncio from elevenlabs import AsyncElevenLabs client = AsyncElevenLabs( api_key="YOUR_API_KEY", ) async def main() -> None: await client.text_to_speech.convert( voice_id="JBFqnCBsd6RMkjVDRZzb", output_format="mp3_44100_128", text="The first move is what sets everything in motion.", model_id="eleven_multilingual_v2", ) asyncio.run(main()) r9r:r;r<r=rArBrCrDNrJrKrLrMrNrOrPrRrrVrWr r rrXrYrrZrSr[ aiter_bytesareadr r^rrrGrrr6r_s r!rdzAsyncTextToSpeechClient.convertsf''44;; !1(!; < ="0.H!. $!."I*}PW#6]=%/TU%6 !.&(<$4"0,D%* 2,A<! 6 S6 SB W)//5#5M\Mh/"5"5lD"InrK(1(=(=(=(U%%f$ oo'''((C/2 /*&9(1(8"+!1y'<'<>R Rm6 SJ%(UO6 S6 S6 SP(# W9+@+@y~~VV Wi6 S6 S6 SsBGE*G F2 AF E.E,E.F/F0A#FF2*G,E..F0 G;E><GF+F//F22G8F; 9GGcK|jjjdt|dd|||d|||t |t dt | t jtd| | | | |||d dd i|t d {} d |jcxkrd kr:nn7t jttt|jS|jdk(r@tt jt tt |j|j}t%|j|7#t"$r"t%|j|j&wxYww)a Generate speech from text with precise character-level timing information for audio-text synchronization. Parameters ---------- voice_id : str Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices. text : str The text that will get converted into speech. 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. optimize_streaming_latency : typing.Optional[int] You can turn on latency optimizations at some cost of quality. The best possible final latency varies by model. Possible values: 0 - default mode (no latency optimizations) 1 - normal latency optimizations (about 50% of possible latency improvement of option 3) 2 - strong latency optimizations (about 75% of possible latency improvement of option 3) 3 - max latency optimizations 4 - max latency optimizations, but also with text normalizer turned off for even more latency savings (best latency, but can mispronounce eg numbers and dates). Defaults to None. output_format : typing.Optional[OutputFormat] The output format of the generated audio. model_id : typing.Optional[str] Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property. language_code : typing.Optional[str] Language code (ISO 639-1) used to enforce a language for the model. Currently only Turbo v2.5 and Flash v2.5 support language enforcement. For other models, an error will be returned if language code is provided. voice_settings : typing.Optional[VoiceSettings] Voice settings overriding stored settings for the given voice. They are applied only on the given request. pronunciation_dictionary_locators : typing.Optional[typing.Sequence[PronunciationDictionaryVersionLocator]] A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request seed : typing.Optional[int] If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295. previous_text : typing.Optional[str] The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. next_text : typing.Optional[str] The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. previous_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that were generated before this generation. Can be used to improve the speech's continuity when splitting up a large task into multiple requests. The results will be best when the same model is used across the generations. In case both previous_text and previous_request_ids is send, previous_text will be ignored. A maximum of 3 request_ids can be send. next_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that come after this generation. next_request_ids is especially useful for maintaining the speech's continuity when regenerating a sample that has had some audio quality issues. For example, if you have generated 3 speech clips, and you want to improve clip 2, passing the request id of clip 3 as a next_request_id (and that of clip 1 as a previous_request_id) will help maintain natural flow in the combined speech. The results will be best when the same model is used across the generations. In case both next_text and next_request_ids is send, next_text will be ignored. A maximum of 3 request_ids can be send. use_pvc_as_ivc : typing.Optional[bool] If true, we won't use PVC version of the voice for the generation but the IVC version. This is a temporary workaround for higher latency in PVC versions. apply_text_normalization : typing.Optional[BodyTextToSpeechWithTimestampsV1TextToSpeechVoiceIdWithTimestampsPostApplyTextNormalization] This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. Cannot be turned on for 'eleven_turbo_v2_5' model. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AudioWithTimestampsResponseModel Successful Response Examples -------- import asyncio from elevenlabs import AsyncElevenLabs client = AsyncElevenLabs( api_key="YOUR_API_KEY", ) async def main() -> None: await client.text_to_speech.convert_with_timestamps( voice_id="21m00Tcm4TlvDq8ikWAM", text="This is a test for the API of ElevenLabs.", ) asyncio.run(main()) r9rfr:r;r<r=rArBrCrDNrJrKrPrOrRrgris r!rjz/AsyncTextToSpeechClient.convert_with_timestampsqsb..;;CC !1(!; < ) 0$$+.KK+&"5$-NN$4'^^-N9#8#8~NNq! l Sy'<'<9>>R R Ss8BFEF AEFAE;F+E??FcK|jjjdt|dd|||d|||t |t dt | t jtd| | | | |||d dd i|t 4d {} d |jcxkrd kr:nn7||jddnd}|j|23d {}||jd {|jdk(r@tt jt t#t |j%|j%}t)|j|776 d d d d {7y 7#t&$r"t)|j|j*wxYw#1d {7swYy xYww)a Converts text into speech using a voice of your choice and returns audio as an audio stream. Parameters ---------- voice_id : str Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices. text : str The text that will get converted into speech. 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. optimize_streaming_latency : typing.Optional[int] You can turn on latency optimizations at some cost of quality. The best possible final latency varies by model. Possible values: 0 - default mode (no latency optimizations) 1 - normal latency optimizations (about 50% of possible latency improvement of option 3) 2 - strong latency optimizations (about 75% of possible latency improvement of option 3) 3 - max latency optimizations 4 - max latency optimizations, but also with text normalizer turned off for even more latency savings (best latency, but can mispronounce eg numbers and dates). Defaults to None. output_format : typing.Optional[OutputFormat] The output format of the generated audio. model_id : typing.Optional[str] Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property. language_code : typing.Optional[str] Language code (ISO 639-1) used to enforce a language for the model. Currently only Turbo v2.5 and Flash v2.5 support language enforcement. For other models, an error will be returned if language code is provided. voice_settings : typing.Optional[VoiceSettings] Voice settings overriding stored settings for the given voice. They are applied only on the given request. pronunciation_dictionary_locators : typing.Optional[typing.Sequence[PronunciationDictionaryVersionLocator]] A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request seed : typing.Optional[int] If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295. previous_text : typing.Optional[str] The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. next_text : typing.Optional[str] The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. previous_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that were generated before this generation. Can be used to improve the speech's continuity when splitting up a large task into multiple requests. The results will be best when the same model is used across the generations. In case both previous_text and previous_request_ids is send, previous_text will be ignored. A maximum of 3 request_ids can be send. next_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that come after this generation. next_request_ids is especially useful for maintaining the speech's continuity when regenerating a sample that has had some audio quality issues. For example, if you have generated 3 speech clips, and you want to improve clip 2, passing the request id of clip 3 as a next_request_id (and that of clip 1 as a previous_request_id) will help maintain natural flow in the combined speech. The results will be best when the same model is used across the generations. In case both next_text and next_request_ids is send, next_text will be ignored. A maximum of 3 request_ids can be send. use_pvc_as_ivc : typing.Optional[bool] If true, we won't use PVC version of the voice for the generation but the IVC version. This is a temporary workaround for higher latency in PVC versions. apply_text_normalization : typing.Optional[BodyTextToSpeechStreamingV1TextToSpeechVoiceIdStreamPostApplyTextNormalization] This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. Cannot be turned on for 'eleven_turbo_v2_5' model. request_options : typing.Optional[RequestOptions] Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response. Yields ------ typing.AsyncIterator[bytes] Streaming audio data Examples -------- import asyncio from elevenlabs import AsyncElevenLabs client = AsyncElevenLabs( api_key="YOUR_API_KEY", ) async def main() -> None: await client.text_to_speech.convert_as_stream( voice_id="JBFqnCBsd6RMkjVDRZzb", output_format="mp3_44100_128", text="The first move is what sets everything in motion.", model_id="eleven_multilingual_v2", ) asyncio.run(main()) r9rlr:r;r<r=rArBrCrDNrJrKrLrMrNrOrPrRrr_s r!rmz)AsyncTextToSpeechClient.convert_as_streamsf''44;; !1(!; R Rm6 SJ%(UO6 S6 S6 SP(# W9+@+@y~~VV Wi6 S6 S6 SsBGE+ G F3AFE/E-E/F0F1A#FF3+G-E//F1 G<E?=GF+F00F33G9F< :GGcK|jjjdt|dd|||d|||t |t dt | t jtd| | | | |||d dd i|t 4d {} d |jcxkrd krlnni|j23d {} t|dk(rt jtttt!j"|Y|j%d {|jdk(r@t't jt(tt(|j!|j!}t-|j|77#YxYw6 d d d d {7y 7#t*$r"t-|j|j.wxYw#1d {7swYy xYww)a Converts text into speech using a voice of your choice and returns a stream of JSONs containing audio as a base64 encoded string together with information on when which character was spoken. Parameters ---------- voice_id : str Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices to list all the available voices. text : str The text that will get converted into speech. 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. optimize_streaming_latency : typing.Optional[int] You can turn on latency optimizations at some cost of quality. The best possible final latency varies by model. Possible values: 0 - default mode (no latency optimizations) 1 - normal latency optimizations (about 50% of possible latency improvement of option 3) 2 - strong latency optimizations (about 75% of possible latency improvement of option 3) 3 - max latency optimizations 4 - max latency optimizations, but also with text normalizer turned off for even more latency savings (best latency, but can mispronounce eg numbers and dates). Defaults to None. output_format : typing.Optional[OutputFormat] The output format of the generated audio. model_id : typing.Optional[str] Identifier of the model that will be used, you can query them using GET /v1/models. The model needs to have support for text to speech, you can check this using the can_do_text_to_speech property. language_code : typing.Optional[str] Language code (ISO 639-1) used to enforce a language for the model. Currently only Turbo v2.5 and Flash v2.5 support language enforcement. For other models, an error will be returned if language code is provided. voice_settings : typing.Optional[VoiceSettings] Voice settings overriding stored settings for the given voice. They are applied only on the given request. pronunciation_dictionary_locators : typing.Optional[typing.Sequence[PronunciationDictionaryVersionLocator]] A list of pronunciation dictionary locators (id, version_id) to be applied to the text. They will be applied in order. You may have up to 3 locators per request seed : typing.Optional[int] If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be integer between 0 and 4294967295. previous_text : typing.Optional[str] The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. next_text : typing.Optional[str] The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation. previous_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that were generated before this generation. Can be used to improve the speech's continuity when splitting up a large task into multiple requests. The results will be best when the same model is used across the generations. In case both previous_text and previous_request_ids is send, previous_text will be ignored. A maximum of 3 request_ids can be send. next_request_ids : typing.Optional[typing.Sequence[str]] A list of request_id of the samples that come after this generation. next_request_ids is especially useful for maintaining the speech's continuity when regenerating a sample that has had some audio quality issues. For example, if you have generated 3 speech clips, and you want to improve clip 2, passing the request id of clip 3 as a next_request_id (and that of clip 1 as a previous_request_id) will help maintain natural flow in the combined speech. The results will be best when the same model is used across the generations. In case both next_text and next_request_ids is send, next_text will be ignored. A maximum of 3 request_ids can be send. use_pvc_as_ivc : typing.Optional[bool] If true, we won't use PVC version of the voice for the generation but the IVC version. This is a temporary workaround for higher latency in PVC versions. apply_text_normalization : typing.Optional[BodyTextToSpeechStreamingWithTimestampsV1TextToSpeechVoiceIdStreamWithTimestampsPostApplyTextNormalization] This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. Cannot be turned on for 'eleven_turbo_v2_5' model. request_options : typing.Optional[RequestOptions] Request-specific configuration. Yields ------ typing.AsyncIterator[StreamingAudioChunkWithTimestampsResponseModel] Stream of JSON objects containing audio chunks and character timing information Examples -------- import asyncio from elevenlabs import AsyncElevenLabs client = AsyncElevenLabs( api_key="YOUR_API_KEY", ) async def main() -> None: response = await client.text_to_speech.stream_with_timestamps( voice_id="JBFqnCBsd6RMkjVDRZzb", output_format="mp3_44100_128", text="The first move is what sets everything in motion.", model_id="eleven_multilingual_v2", ) async for chunk in response: yield chunk asyncio.run(main()) r9ror:r;r<r=rArBrCrDNrJrKrrPrOrR)rrVrWr r rrXrYrrZrS aiter_linesrqr^rrrGrrrr rrrr6rss r!ruz.AsyncTextToSpeechClient.stream_with_timestampss.j''44;; !1(!; < ! !e !"5zQ ("(++ N .*X,0JJu,=!"# oo'''((C/2 /*&9(1(8"+!1y'<'<>R RA@ SH !! (?c@ S@ S@ Sd(# W9+@+@y~~VV W}@ S@ S@ SsBHF H G-(F?6F):F ;F)>F?F"F??F"F?"F=#A#F?G-H F)"F&$F?+ H6F97H=F??+G**G--G?3G6 4G?;H)rvrwrxrr"rZryrXrzr{r|rrrYrr r AsyncIteratorr~rdrrrjrrmrrrurr$r!rrs.*<.15;?7;)-.29= %).2*.FJBF04 ;?/iSiS iS - iS %+OOC$8 iS|4iS//#&iSs+iS 6iS,2?? OOA B, iSooc"iSs+iS ??3'!iS"%oofooc.BC#iS$!//&//#*>?%iS&-'iS(#)// K# )iS. 8/iS0   e $1iS`15;?7;)-.29= %).2*.FJBF04 ;?/iOiO iO - iO %+OOC$8 iO|4iO//#&iOs+iO 6iO,2?? OOA B, iOooc"iOs+iO ??3'!iO"%oofooc.BC#iO$!//&//#*>?%iO&-'iO(#)// g# )iO. 8/iO0 *1iO`15;?7;)-.29= %).2*.FJBF04 ;?/iSiS iS - iS %+OOC$8 iS|4iS//#&iSs+iS 6iS,2?? OOA B, iSooc"iSs+iS ??3'!iS"%oofooc.BC#iS$!//&//#*>?%iS&-'iS(#)// Z# )iS. 8/iS0   e $1iS`15;?7;)-.29= %).2*.FJBF04 ;?/uSuS uS - uS %+OOC$8 uS|4uS//#&uSs+uS 6uS,2?? OOA B, uSooc"uSs+uS ??3'!uS"%oofooc.BC#uS$!//&//#*>?%uS&-'uS(#)// v# )uS. 8/uS0   L M1uSr$r),rXcore.client_wrapperrtypes.output_formatrtypes.voice_settingsr.types.pronunciation_dictionary_version_locatorrStypes.body_text_to_speech_v_1_text_to_speech_voice_id_post_apply_text_normalizationr core.request_optionsr core.jsonable_encoderr core.serializationr !errors.unprocessable_entity_errorr types.http_validation_errorrcore.unchecked_base_modelr json.decoderrcore.api_errorrstypes.body_text_to_speech_with_timestamps_v_1_text_to_speech_voice_id_with_timestamps_post_apply_text_normalizationr*types.audio_with_timestamps_response_modelrdtypes.body_text_to_speech_streaming_v_1_text_to_speech_voice_id_stream_post_apply_text_normalizationrڄtypes.body_text_to_speech_streaming_with_timestamps_v_1_text_to_speech_voice_id_stream_with_timestamps_post_apply_text_normalizationr:types.streaming_audio_chunk_with_timestamps_response_modelrrGrr^AnyrZrrrr$r!rs3.0b24HH=6(%Zx 4v{{6::s#Z SZ Szz Sz Sr$