o "iQ @sddlZddlZddlZddlZddlZddlmZmZmZmZmZddl m Z m Z ddl m Z mZddlmZmZmZmZddlmZddlmZed d ed d d dddZeZeZeZdedefddZeej dZ!Gddde Z"Gddde Z#dS)N)IteratorOptionalUnionr AsyncIterator)BaseElevenLabsAsyncBaseElevenLabs)RequestOptionsApiError)Voice VoiceSettings%PronunciationDictionaryVersionLocatorModel)ElevenLabsEnvironment)RealtimeTextToSpeechClientEXAVITQu4vr4xnSDxMaLRachelgQ?g?gT) stabilitysimilarity_booststyleuse_speaker_boost)voice_idnamesettingsvalreturncCsttd|S)Nz^[a-zA-Z0-9]{20}$)boolrematch)rrU/var/www/html/voicebot/backend/venv/lib/python3.10/site-packages/elevenlabs/client.py is_voice_id"sr!.cs4eZdZdZdejedddddej e dedej e d ej e d ej e j f fd d Z  d$d e deje de dej e dej edef ddZeejddddedddee ee fdeeeefdej edeeefdej eded e e d!ej eje dej edee!ee!ffd"d#Z"Z#S)% ElevenLabsa Use this class to access the different functions within the SDK. You can instantiate any number of clients with different configuration that will propogate to these functions. Parameters: - base_url: typing.Optional[str]. The base url to use for requests from the client. - environment: ElevenLabsEnvironment. The environment to use for requests from the client. from .environment import ElevenLabsEnvironment Defaults to ElevenLabsEnvironment.PRODUCTION - api_key: typing.Optional[str]. - timeout: typing.Optional[float]. The timeout to be used, in seconds, for requests by default the timeout is 60 seconds. - httpx_client: typing.Optional[httpx.Client]. The httpx client to use for making requests, a preconfigured client is used by default, however this is useful should you want to pass in any custom httpx configuration. --- from elevenlabs.client import ElevenLabs client = ElevenLabs( api_key="YOUR_API_KEY", ) NELEVEN_API_KEY<base_url environmentapi_keytimeout httpx_clientr&r'r(r)r*cs(tj|||||dt|jd|_dS)Nr%)client_wrapper)super__init__r_client_wrappertext_to_speech)selfr&r'r(r)r* __class__rr r-As zElevenLabs.__init__rfiles descriptionlabelsrequest_optionsrcCs>|jj||dd|Dtt|pid}|jj|j|dS)a This is a manually maintained helper function that clones a voice from a set of audio files. **NOTE**: This function is a helper function and is simply making calls to the `add` and `get` functions of the `voices` endpoint. Parameters: - name: str. The name that identifies this voice. This will be displayed in the dropdown of the website. - files: typing.List[str]. The filepaths of the audio files to be used to create the voice. - description: str. How would you describe the voice? - labels: str. Serialized labels dictionary for the voice. - request_options: typing.Optional[RequestOptions]. Request-specific configuration. cSg|]}t|dqSrbopen.0filerrr nz$ElevenLabs.clone..rr4r3r5r6voicesaddstrjsondumpsgetrr0rr3r4r5r6add_voice_responserrr cloneSs zElevenLabs.cloneeleven_monolingual_v1rF mp3_44100_128voicevoice_settingsmodeloptimize_streaming_latencystream output_format!pronunciation_dictionary_locatorsr6textrPrQrRrSrTrUrVc  sJttr tr } nGttr:|jj| d} td| tfdd| jDd} | dur7tddd| } nttrPj } |t j krOj durOj }nt j } t|tr[|} nt|t rc|j } |rt|trx|jj| ||||| || d St|tr|jj| ||| | d Std dt|tstd d|jj| | ||||| |d S)uP - text: Union[str, Iterator[str]]. The string or stream of strings that will get converted into speech. - voice: str. A voice id, name, or voice response. Defaults to the Rachel voice. - model: 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. - 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 0. - stream: bool. If true, the function will return a generator that will yield the audio in chunks. Defaults to False. - output_format: typing.Optional[str]. Output format of the generated audio. Must be one of: mp3_22050_32 - output format, mp3 with 22.05kHz sample rate at 32kbps. mp3_44100_32 - output format, mp3 with 44.1kHz sample rate at 32kbps. mp3_44100_64 - output format, mp3 with 44.1kHz sample rate at 64kbps. mp3_44100_96 - output format, mp3 with 44.1kHz sample rate at 96kbps. mp3_44100_128 - default output format, mp3 with 44.1kHz sample rate at 128kbps. mp3_44100_192 - output format, mp3 with 44.1kHz sample rate at 192kbps. Requires you to be subscribed to Creator tier or above. pcm_16000 - PCM format (S16LE) with 16kHz sample rate. pcm_22050 - PCM format (S16LE) with 22.05kHz sample rate. pcm_24000 - PCM format (S16LE) with 24kHz sample rate. pcm_44100 - PCM format (S16LE) with 44.1kHz sample rate. Requires you to be subscribed to Independent Publisher tier or above. ulaw_8000 - μ-law format (sometimes written mu-law, often approximated as u-law) with 8kHz sample rate. Note that this format is commonly used for Twilio audio inputs. Defaults to mp3_44100_128. - voice_settings: typing.Optional[VoiceSettings]. Voice settings overriding stored setttings 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 - request_options: typing.Optional[RequestOptions]. Request-specific configuration. rBvoices_responsec3 |] }|jkr|jVqdSNrrr=vrPrr z&ElevenLabs.generate..NVoice not found.body)rrQrSrUrWr6rVmodel_id)rrQrWr6rez)Text is neither a string nor an iterator.+Text must be a string when stream is False.rrerQrSrUrWr6rV) isinstancerFr!rDget_allprintnextr r r DEFAULT_VOICErrrer/convert_as_streamrconvert_realtimeconvertr0rWrPrQrRrSrTrUrVr6rrXmaybe_voice_idrerr^r generatevsj:            zElevenLabs.generate)NN)$__name__ __module__ __qualname____doc__r PRODUCTIONosgetenvtypingrrFfloathttpxClientr-Listr r rLrlrOMITrrVoiceId VoiceNamer ModelIdrintrSequencer bytesrr __classcell__rrr1r r"*s  '     r"c@seZdZdZ ddedejedededejede f d d Z e e j d d d de dddedeeee fdejedeeefdejededeedejejedejedeeeeffddZdS)AsyncElevenLabsa( Use this class to access the different functions within the SDK. You can instantiate any number of clients with different configuration that will propogate to these functions. Parameters: - base_url: typing.Optional[str]. The base url to use for requests from the client. - environment: ElevenLabsEnvironment. The environment to use for requests from the client. from .environment import ElevenLabsEnvironment Defaults to ElevenLabsEnvironment.PRODUCTION - api_key: typing.Optional[str]. - timeout: typing.Optional[float]. The timeout to be used, in seconds, for requests by default the timeout is 60 seconds. - httpx_client: typing.Optional[httpx.AsyncClient]. The httpx client to use for making requests, a preconfigured client is used by default, however this is useful should you want to pass in any custom httpx configuration. --- from elevenlabs.client import AsyncElevenLabs client = AsyncElevenLabs( api_key="YOUR_API_KEY", ) Nrr3r4r5r6rcsL|jj||dd|Dtt|pidIdH}|jj|j|dIdHS)a This is a manually mnaintained helper function that generates a voice from provided text. **NOTE**: This function is a helper function and is simply making calls to the `text_to_speech.convert` and`text_to_speech.convert_as_stream` functions. Parameters: - name: str. The name that identifies this voice. This will be displayed in the dropdown of the website. - files: typing.List[str]. The filepaths of the audio files to be used to create the voice. - description: str. How would you describe the voice? - labels: str. Serialized labels dictionary for the voice. - request_options: typing.Optional[RequestOptions]. Request-specific configuration. cSr7r8r:r<rrr r?"r@z)AsyncElevenLabs.clone..rANrBrCrJrrr rLs   zAsyncElevenLabs.clonerMrFrNrOrWrPrQrRrSrTrUrVc  sttr tr } nCttr7|jj| dIdH} tfdd| jDd} | s4tddd| } nttrMj} |t j krLj durLj }nt j} t|trX|} nt|t r`|j } |rp|j j| | ||||| |dSt|tsztd d|j j| | ||||| |dS) u{ This is a manually mnaintained helper function that generates a voice from provided text. **NOTE**: This function is a helper function and is simply making calls to the `text_to_speech.convert` and`text_to_speech.convert_as_stream` functions. - text: str. The string that will get converted into speech. The Async client does not support streaming. - voice: str. A voice id, name, or voice response. Defaults to the Rachel voice. - model: 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. - 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 0. - stream: bool. If true, the function will return a generator that will yield the audio in chunks. Defaults to False. - output_format: typing.Optional[str]. Output format of the generated audio. Must be one of: mp3_22050_32 - output format, mp3 with 22.05kHz sample rate at 32kbps. mp3_44100_32 - output format, mp3 with 44.1kHz sample rate at 32kbps. mp3_44100_64 - output format, mp3 with 44.1kHz sample rate at 64kbps. mp3_44100_96 - output format, mp3 with 44.1kHz sample rate at 96kbps. mp3_44100_128 - default output format, mp3 with 44.1kHz sample rate at 128kbps. mp3_44100_192 - output format, mp3 with 44.1kHz sample rate at 192kbps. Requires you to be subscribed to Creator tier or above. pcm_16000 - PCM format (S16LE) with 16kHz sample rate. pcm_22050 - PCM format (S16LE) with 22.05kHz sample rate. pcm_24000 - PCM format (S16LE) with 24kHz sample rate. pcm_44100 - PCM format (S16LE) with 44.1kHz sample rate. Requires you to be subscribed to Independent Publisher tier or above. ulaw_8000 - μ-law format (sometimes written mu-law, often approximated as u-law) with 8kHz sample rate. Note that this format is commonly used for Twilio audio inputs. Defaults to mp3_44100_128. - voice_settings: typing.Optional[VoiceSettings]. Voice settings overriding stored setttings 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 - request_options: typing.Optional[RequestOptions]. Request-specific configuration. rBNc3rYrZr[r\r^rr r_or`z+AsyncElevenLabs.generate..rarbrcrgrf)rhrFr!rDrirkr r rrlrrrer/rmrorprr^r rr*sVA       zAsyncElevenLabs.generaterZ)rsrtrurvrFrzr~rr r rLrlrrrrrr rrrrrr rrrrrrrr rs^ *     r)$rzrGrrxr|rrrr base_clientrrcorer r typesr r r rr'r realtime_ttsrrlrFrrrrr!castAnyrr"rrrrr s4  C