o lWiH@sVddlZddlZddlZddlmZddlmZddlmZm Z ddl m Z m Z ddl mZddlmZdd lmZdd lmZdd lmZdd lmZdd lmZddlmZddlmZddlm Z ddl!m"Z"ddl#m$Z$ddl%m&Z&ddl'm(Z(ddl)m*Z*ddl+m,Z,ddl-m.Z.ddl/m0Z0e1ej2dZ3GdddZ4GdddZ5dS)N)JSONDecodeError)ApiError)AsyncClientWrapperSyncClientWrapper)AsyncHttpResponse HttpResponse)RequestOptions)'convert_and_respect_annotation_metadata)construct_type)UnprocessableEntityError)0AudioWithTimestampsAndVoiceSegmentsResponseModel) DialogueInput)HttpValidationError)ModelSettingsResponseModel)%PronunciationDictionaryVersionLocator)>StreamingAudioChunkWithTimestampsAndVoiceSegmentsResponseModel):BodyTextToDialogueFullWithTimestampsApplyTextNormalization)UBodyTextToDialogueMultiVoiceStreamingV1TextToDialogueStreamPostApplyTextNormalization)FBodyTextToDialogueMultiVoiceV1TextToDialoguePostApplyTextNormalization)zCRawTextToDialogueClient.convert.._stream..rHresponsedatatype_r9rCbody status_coderCrXrZgetr iter_bytesreadr dictrCtypingcastrr rBrrtext _chunk_size_response_json _responser1r%r&_stream2  z0RawTextToDialogueClient.convert.._streamN r" httpx_clientstreamr r`SequencerrrOMITrIteratorbytes r$r2r*r+r,r-r.r/r0r1rhr%rfr&convert6>7  "zRawTextToDialogueClient.convertc #r4)u Converts a list of text and voice ID pairs into speech (dialogue) and returns an audio stream. Parameters ---------- inputs : typing.Sequence[DialogueInput] A list of dialogue inputs, each containing text and a voice ID which will be converted into speech. output_format : typing.Optional[TextToDialogueStreamRequestOutputFormat] Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. 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 and text normalization. If the model does not support provided language code, an error will be returned. settings : typing.Optional[ModelSettingsResponseModel] Settings controlling the dialogue generation. 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. apply_text_normalization : typing.Optional[BodyTextToDialogueMultiVoiceStreamingV1TextToDialogueStreamPostApplyTextNormalization] 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. 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. Returns ------- typing.Iterator[HttpResponse[typing.Iterator[bytes]]] Streaming audio data v1/text-to-dialogue/streamr6r*r7r8r<r=r>r?r3c rE) NrFrGrHrIcsrJr r%rKr%r%r&rNrOzBRawTextToDialogueClient.stream.._stream..rPrQrTrUrWrYr[rcrfr%r&rhriz/RawTextToDialogueClient.stream.._streamNrjrqr%rfr&rlrszRawTextToDialogueClient.streamc #s|jjjddd|it|tjtdd||t|tddt|tjtdd||dddi| t d d t tj t ffd d } | VWd d S1sNwYd S)u Converts a list of text and voice ID pairs into speech (dialogue) and returns a stream of JSON blobs containing audio as a base64 encoded string and timestamps Parameters ---------- inputs : typing.Sequence[DialogueInput] A list of dialogue inputs, each containing text and a voice ID which will be converted into speech. output_format : typing.Optional[TextToDialogueStreamWithTimestampsRequestOutputFormat] Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. 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 and text normalization. If the model does not support provided language code, an error will be returned. settings : typing.Optional[ModelSettingsResponseModel] Settings controlling the dialogue generation. 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. apply_text_normalization : typing.Optional[BodyTextToDialogueStreamWithTimestampsApplyTextNormalization] 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. request_options : typing.Optional[RequestOptions] Request-specific configuration. Yields ------ typing.Iterator[HttpResponse[typing.Iterator[StreamingAudioChunkWithTimestampsAndVoiceSegmentsResponseModel]]] Stream of transcription chunks *v1/text-to-dialogue/stream/with-timestampsr6r*r7r8r<r=r>r?r3c sz=djkr dkrnnfdd}t|dWSjdkr8ttjttt t dd }Wnt yPt jtjj d wt jtj|d ) NrFrGc 3sVD]#}zt|dkrWqttttt|dVWqty(YqwdSNrrU) iter_lineslenr`rarr rBloads Exception_textrgr%r&_iterqs    zNRawTextToDialogueClient.stream_with_timestamps.._stream.._iterrQrTrUrWrY)rZrr^r r_rCr`rarr rBrrrbr~rer}r%r&rhks.   z?RawTextToDialogueClient.stream_with_timestamps.._streamN) r"rkrlr r`rmrrrrnrrorrqr%r}r&stream_with_timestampssB5  *"z.RawTextToDialogueClient.stream_with_timestampsc Cs|jjjddd|it|tjtdd||t|tddt|tjtdd||dddi| t d } z>d | j kr;d krPnnt t t t | d } t| | d WS| j dkrhtt| jt tt t| d d| } Wntyt| j t| j| jdwt| j t| j| d)u Generate dialogue from text with precise character-level timing information for audio-text synchronization. Parameters ---------- inputs : typing.Sequence[DialogueInput] A list of dialogue inputs, each containing text and a voice ID which will be converted into speech. output_format : typing.Optional[TextToDialogueConvertWithTimestampsRequestOutputFormat] Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. 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 and text normalization. If the model does not support provided language code, an error will be returned. settings : typing.Optional[ModelSettingsResponseModel] Settings controlling the dialogue generation. 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. apply_text_normalization : typing.Optional[BodyTextToDialogueFullWithTimestampsApplyTextNormalization] 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. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- HttpResponse[AudioWithTimestampsAndVoiceSegmentsResponseModel] Successful Response #v1/text-to-dialogue/with-timestampsr6r*r7r8r<r=r>r?rFrGrUrQrTrWrY)r"rkrequestr r`rmrrrrnrZrar r rBrr r_rCrrrrb r$r2r*r+r,r-r.r/r0r1rg_datarer%r%r&convert_with_timestampssh4   z/RawTextToDialogueClient.convert_with_timestamps)"__name__ __module__ __qualname__rr' contextlibcontextmanagerrnr`rmrOptionalrstrrrintrr rorrprrrrrlrrrrrrr rr%r%r%r&r2s    p   p       rc@r)AsyncRawTextToDialogueClientrcCrr r!r#r%r%r&r'r(z%AsyncRawTextToDialogueClient.__init__Nr)r2r*r+r,r-r.r/r0r1r3c |jjjddd|it|tjtdd||t|tddt|tjtdd||dddit d 4Id H"d t tj t ffd d } | Id HVWd Id Hd S1Id Hs\wYd S)u Converts a list of text and voice ID pairs into speech (dialogue) and returns audio. Parameters ---------- inputs : typing.Sequence[DialogueInput] A list of dialogue inputs, each containing text and a voice ID which will be converted into speech. output_format : typing.Optional[TextToDialogueConvertRequestOutputFormat] Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. 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 and text normalization. If the model does not support provided language code, an error will be returned. settings : typing.Optional[ModelSettingsResponseModel] Settings controlling the dialogue generation. 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. apply_text_normalization : typing.Optional[BodyTextToDialogueMultiVoiceV1TextToDialoguePostApplyTextNormalization] 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. 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. Returns ------- typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[bytes]]] The generated audio file r5r6r*r7r8r<r=r>r?Nr3c zNdjkr dkr+nndurddnd}tddj|d2dWSIdHjd krJttjt t t t d d  }Wnt ybtjtjjd wtjtj|d ) NrFrGrHrIcS|z 3dHW}|Vq6dSr r%rKr%r%r&rNbzHAsyncRawTextToDialogueClient.convert.._stream..rPrQrTrUrWrYrZr\r aiter_bytesareadr r_rCr`rarr rBrrrbrcrfr%r&rh\6  z5AsyncRawTextToDialogueClient.convert.._stream r"rkrlr r`rmrrrrnr AsyncIteratorrprqr%rfr&rr>7 .z$AsyncRawTextToDialogueClient.convertc r)u Converts a list of text and voice ID pairs into speech (dialogue) and returns an audio stream. Parameters ---------- inputs : typing.Sequence[DialogueInput] A list of dialogue inputs, each containing text and a voice ID which will be converted into speech. output_format : typing.Optional[TextToDialogueStreamRequestOutputFormat] Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. 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 and text normalization. If the model does not support provided language code, an error will be returned. settings : typing.Optional[ModelSettingsResponseModel] Settings controlling the dialogue generation. 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. apply_text_normalization : typing.Optional[BodyTextToDialogueMultiVoiceStreamingV1TextToDialogueStreamPostApplyTextNormalization] 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. 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. Returns ------- typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[bytes]]] Streaming audio data rtr6r*r7r8r<r=r>r?Nr3c r) NrFrGrHrIcSrr r%rKr%r%r&rNrzGAsyncRawTextToDialogueClient.stream.._stream..rPrQrTrUrWrYrrcrfr%r&rhrz4AsyncRawTextToDialogueClient.stream.._streamrrqr%rfr&rlyrz#AsyncRawTextToDialogueClient.streamc s|jjjddd|it|tjtdd||t|tddt|tjtdd||dddi| t d 4Id H!d t tj t ffd d } | Id HVWd Id Hd S1Id Hs[wYd S)u" Converts a list of text and voice ID pairs into speech (dialogue) and returns a stream of JSON blobs containing audio as a base64 encoded string and timestamps Parameters ---------- inputs : typing.Sequence[DialogueInput] A list of dialogue inputs, each containing text and a voice ID which will be converted into speech. output_format : typing.Optional[TextToDialogueStreamWithTimestampsRequestOutputFormat] Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. 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 and text normalization. If the model does not support provided language code, an error will be returned. settings : typing.Optional[ModelSettingsResponseModel] Settings controlling the dialogue generation. 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. apply_text_normalization : typing.Optional[BodyTextToDialogueStreamWithTimestampsApplyTextNormalization] 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. request_options : typing.Optional[RequestOptions] Request-specific configuration. Yields ------ typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[StreamingAudioChunkWithTimestampsAndVoiceSegmentsResponseModel]]] Stream of transcription chunks rur6r*r7r8r<r=r>r?Nr3c sz@djkr dkrnnfdd}t|dWSIdHjdkr._stream.._iterrQrTrUrWrY)rZrrr r_rCr`rarr rBrrrbrr}r%r&rh@s0   zDAsyncRawTextToDialogueClient.stream_with_timestamps.._stream) r"rkrlr r`rmrrrrnrrrrqr%r}r&rsB7 *.z3AsyncRawTextToDialogueClient.stream_with_timestampsc s |jjjddd|it|tjtdd||t|tddt|tjtdd||dddi| t d Id H} z>d | j kr?d krTnnt t t t | d } t| | dWS| j dkrltt| jt tt t| d d| } Wntyt| j t| j| jdwt| j t| j| d)u Generate dialogue from text with precise character-level timing information for audio-text synchronization. Parameters ---------- inputs : typing.Sequence[DialogueInput] A list of dialogue inputs, each containing text and a voice ID which will be converted into speech. output_format : typing.Optional[TextToDialogueConvertWithTimestampsRequestOutputFormat] Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs. 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 and text normalization. If the model does not support provided language code, an error will be returned. settings : typing.Optional[ModelSettingsResponseModel] Settings controlling the dialogue generation. 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. apply_text_normalization : typing.Optional[BodyTextToDialogueFullWithTimestampsApplyTextNormalization] 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. request_options : typing.Optional[RequestOptions] Request-specific configuration. Returns ------- AsyncHttpResponse[AudioWithTimestampsAndVoiceSegmentsResponseModel] Successful Response rr6r*r7r8r<r=r>r?NrFrGrUrQrTrWrY)r"rkrr r`rmrrrrnrZrar r rBrr r_rCrrrrbrr%r%r&rlsj4    z4AsyncRawTextToDialogueClient.convert_with_timestamps)"rrrrr'rasynccontextmanagerrnr`rmrrrrrrrrr rrrprrrrrlrrrrrrr rr%r%r%r&rs   q   q        r)6rrBr` json.decoderrcore.api_errorrcore.client_wrapperrrcore.http_responserrcore.request_optionsr core.serializationr core.unchecked_base_modelr !errors.unprocessable_entity_errorr =types.audio_with_timestamps_and_voice_segments_response_modelr types.dialogue_inputrtypes.http_validation_errorr#types.model_settings_response_modelr.types.pronunciation_dictionary_version_locatorrMtypes.streaming_audio_chunk_with_timestamps_and_voice_segments_response_modelrItypes.body_text_to_dialogue_full_with_timestamps_apply_text_normalizationrktypes.body_text_to_dialogue_multi_voice_streaming_v_1_text_to_dialogue_stream_post_apply_text_normalizationrZtypes.body_text_to_dialogue_multi_voice_v_1_text_to_dialogue_post_apply_text_normalizationrKtypes.body_text_to_dialogue_stream_with_timestamps_apply_text_normalizationr4types.text_to_dialogue_convert_request_output_formatrDtypes.text_to_dialogue_convert_with_timestamps_request_output_formatr3types.text_to_dialogue_stream_request_output_formatrCtypes.text_to_dialogue_stream_with_timestamps_request_output_formatrraAnyrnrrr%r%r%r&s>                    T