/UiDhddlmZddlZddlmZddlmZddlmZm Z m Z ddl m Z m Z ddlmZmZdd lmZd Zd Ze d Z eGd dZGddej.ZGddej.ZeGddZGddej.ZGddej.Zy)) annotationsN) AsyncIterator) dataclass)AnyCallableLiteral)npnpt) AudioInputStreamedAudioInput)get_sentence_based_splitterzYYou will receive partial sentences. Do not complete the sentence, just read out the text.x) alloyashcoralechofableonyxnovasageshimmerceZdZUdZdZded< dZded< ejZ ded < dZ d ed < d Z d ed< e Z ded< dZded<y)TTSModelSettingszSettings for a TTS model.NzTTSVoice | Nonevoicerint buffer_sizez npt.DTypeLikedtypezYCallable[[npt.NDArray[np.int16 | np.float32]], npt.NDArray[np.int16 | np.float32]] | Nonetransform_datazXYou will receive partial sentences. Do not complete the sentence just read out the text.str instructionsz Callable[[str], tuple[str, str]] text_splitter float | Nonespeed)__name__ __module__ __qualname____doc__r__annotations__rr int16rrr!rr"r$n/home/jay/workspace/tools/ai-image-gen/jaaz-app/server/venv/lib/python3.12/site-packages/agents/voice/model.pyrrs#!E?! KS88E=#= a  c# 7R6SM3S E<Vr,rcfeZdZdZeej ddZej ddZy)TTSModelz?A text-to-speech model that can convert text into audio output.cy)zThe name of the TTS model.Nr+selfs r- model_namezTTSModel.model_nameC r,cy)zGiven a text string, produces a stream of audio bytes, in PCM format. Args: text: The text to convert to audio. Returns: An async iterator of audio bytes, in PCM format. Nr+)r2textsettingss r-runz TTSModel.runI r,Nreturnr )r6r r7rr;zAsyncIterator[bytes]) r%r&r'r(propertyabcabstractmethodr3r8r+r,r-r/r/@s?I        r,r/c\eZdZdZej ddZej ddZy)StreamedTranscriptionSessionz(A streamed transcription of audio input.cy)zYields a stream of text transcriptions. Each transcription is a turn in the conversation. This method is expected to return only after `close()` is called. Nr+r1s r-transcribe_turnsz-StreamedTranscriptionSession.transcribe_turnsYs r,c Kyw)zCloses the session.Nr+r1s r-closez"StreamedTranscriptionSession.closeas  N)r;zAsyncIterator[str])r;None)r%r&r'r(r=r>rBrDr+r,r-r@r@Vs72     r,r@cPeZdZUdZdZded< dZded< dZded< dZded <y) STTModelSettingsz$Settings for a speech-to-text model.N str | Nonepromptlanguager# temperaturezdict[str, Any] | Noneturn_detection) r%r&r'r(rJr)rKrLrMr+r,r-rHrHgs:.FJ/Hj* $K$',0N)0Tr,rHceZdZdZeej ddZej ddZej ddZ y) STTModelz>A speech-to-text model that can convert audio input into text.cy)zThe name of the STT model.Nr+r1s r-r3zSTTModel.model_name{r4r,c Kyw)aGiven an audio input, produces a text transcription. Args: input: The audio input to transcribe. settings: The settings to use for the transcription. trace_include_sensitive_data: Whether to include sensitive data in traces. trace_include_sensitive_audio_data: Whether to include sensitive audio data in traces. Returns: The text transcription of the audio input. Nr+r2inputr7trace_include_sensitive_data"trace_include_sensitive_audio_datas r- transcribezSTTModel.transcribes & rEc Kyw)aCreates a new transcription session, which you can push audio to, and receive a stream of text transcriptions. Args: input: The audio input to transcribe. settings: The settings to use for the transcription. trace_include_sensitive_data: Whether to include sensitive data in traces. trace_include_sensitive_audio_data: Whether to include sensitive audio data in traces. Returns: A new transcription session. Nr+rRs r-create_sessionzSTTModel.create_sessions ( rENr:) rSr r7rHrTboolrUrYr;r ) rSr r7rHrTrYrUrYr;r@) r%r&r'r(r<r=r>r3rVrXr+r,r-rOrOxsH      # '+  -1    (  ! # '+  -1  &   r,rOc\eZdZdZej ddZej ddZy)VoiceModelProviderzThe base interface for a voice model provider. A model provider is responsible for creating speech-to-text and text-to-speech models, given a name. cy)zGet a speech-to-text model by name. Args: model_name: The name of the model to get. Returns: The speech-to-text model. Nr+r2r3s r- get_stt_modelz VoiceModelProvider.get_stt_modelr9r,cy)z#Get a text-to-speech model by name.Nr+r]s r- get_tts_modelz VoiceModelProvider.get_tts_modelsr,N)r3rIr;rO)r3rIr;r/)r%r&r'r(r=r>r^r`r+r,r-r[r[s;       22r,r[) __future__rr=collections.abcr dataclassesrtypingrrrimportsr r rSr r utilsrDEFAULT_TTS_INSTRUCTIONSDEFAULT_TTS_BUFFER_SIZETTSVoicerABCr/r@rHrOr[r+r,r-rks" )!))1.` ^ _9 'W'W 'WT sww , 377 "  U U  U 2 sww2 j22r,