o i' @sDdZddlZddlZddlmZmZddlmZmZm Z m Z m Z m Z ddl mZdejd<ddlmZdd lmZdd lmZmZmZmZdd lmZmZmZdd lmZdd lm Z zddl!Z"ddl#m$m%m&Z'Wn e(yZ)ze*de)e*de+de)dZ)[)wweGdddeZ,GdddeZ-dS)zNVIDIA Riva text-to-speech service implementation. This module provides integration with NVIDIA Riva's TTS services through gRPC API for high-quality speech synthesis. N) dataclassfield)AnyAsyncGenerator AsyncIterator GeneratorMappingOptional) traced_ttsfalseGRPC_ENABLE_FORK_SUPPORT)logger) BaseModel) ErrorFrameFrame StartFrameTTSAudioRawFrame) NOT_GIVEN TTSSettings _NotGiven) TTSService)Languagez Exception: zNIn order to use NVIDIA Riva TTS, you need to `pip install pipecat-ai[nvidia]`.zMissing module: c@s,eZdZUdZedddZeeBed<dS)NvidiaTTSSettingszdSettings for NvidiaTTSService. Parameters: quality: Audio quality setting (0-100). cCstSN)rrrO/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/nvidia/tts.py5szNvidiaTTSSettings.)default_factoryqualityN) __name__ __module__ __qualname____doc__rrintr__annotations__rrrrr-s rcseZdZUdZeZeed<GdddeZdddddd ddd d d e d e de e de e de e e fde ede ede ffddZde fddZdedee efffdd ZddZdd Zd!effd"d# Zed$e d%e deedffd&d'ZZS)(NvidiaTTSServicezNVIDIA Riva text-to-speech service. Provides high-quality text-to-speech synthesis using NVIDIA Riva's cloud-based TTS models. Supports multiple voices, languages, and configurable quality settings. _settingsc@s4eZdZUdZejZeeed<dZ ee ed<dS)zNvidiaTTSService.InputParamsaYInput parameters for Riva TTS configuration. .. deprecated:: 0.0.105 Use ``NvidiaTTSService.Settings`` directly via the ``settings`` parameter instead. Parameters: language: Language code for synthesis. Defaults to US English. quality: Audio quality setting (0-100). Defaults to 20. languagerN) rr r!r"rEN_USr'r r$rr#rrrr InputParamsCs  r*zgrpc.nvcf.nvidia.com:443Nz$877104f7-e885-42b9-8de8-f6e4c6303969zmagpie-tts-multilingual) function_id model_nameT)servervoice_id sample_ratemodel_function_mapparamssettingsuse_sslapi_keyr-r.r/r0r1r2r3c  s|j|ddtjdd} |dur|dd|| _|dur7|d|s7|jdur.|j| _|jdur7|j| _|dur@| |t j d |d d | d | ||_ ||_ |d |_ ||_d|_d|_dS) a;Initialize the NVIDIA Riva TTS service. Args: api_key: NVIDIA API key for authentication. server: gRPC server endpoint. Defaults to NVIDIA's cloud endpoint. voice_id: Voice model identifier. Defaults to multilingual Aria voice. .. deprecated:: 0.0.105 Use ``settings=NvidiaTTSService.Settings(voice=...)`` instead. sample_rate: Audio sample rate. If None, uses service default. model_function_map: Dictionary containing function_id and model_name for the TTS model. params: Additional configuration parameters for TTS synthesis. .. deprecated:: 0.0.105 Use ``settings=NvidiaTTSService.Settings(...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. use_ssl: Whether to use SSL for the NVIDIA Riva server. Defaults to True. **kwargs: Additional arguments passed to parent TTSService. r,zMagpie-Multilingual.EN-US.Ariar()modelvoicer'rNr.r6r1T)r/push_start_framepush_stop_framesr2r+r)Settingsgetrr)"_warn_init_param_moved_to_settingsr6r'r apply_updatesuper__init___server_api_key _function_id_use_ssl_service_config) selfr4r-r.r/r0r1r2r3kwargsdefault_settings __class__rrr>Qs@'       zNvidiaTTSService.__init__r5csRddl}||d|jdtddWddS1s"wYdS)aSet the TTS model. .. deprecated:: 0.0.104 Model cannot be changed after initialization for NVIDIA Riva TTS. Set model and function id in the constructor instead, e.g.:: NvidiaTTSService( api_key=..., model_function_map={"function_id": "", "model_name": ""}, ) Args: model: The model name to set. rNalwaysa'set_model' is deprecated. Model cannot be changed after initialization for NVIDIA Riva TTS. Set model and function id in the constructor instead, e.g.: NvidiaTTSService(api_key=..., model_function_map={'function_id': '', 'model_name': ''})) stacklevel)warningscatch_warnings simplefilterwarnDeprecationWarning)rEr5rMrrr set_models  "zNvidiaTTSService.set_modeldeltareturncs*t|IdH}|s|S|||S)zgApply a settings delta. Settings are stored but not applied to the active connection. N)r=_update_settings _warn_unhandled_updated_settings)rErSchangedrHrrrUs  z!NvidiaTTSService._update_settingscCsP|jdurdSd|jgdd|jgg}tjd|j|j|}tj||_dS)Nz function-id authorizationzBearer ) rCrAr@rivaclientAuthrBr?SpeechSynthesisService)rEmetadataauthrrr_initialize_clients z#NvidiaTTSService._initialize_clientcCs&|jsdS|jjtjjj}|Sr)rCstubGetRivaSynthesisConfigrYrZproto riva_tts_pb2RivaSynthesisConfigRequest)rEconfigrrr_create_synthesis_configs  z)NvidiaTTSService._create_synthesis_configframecs>t|IdH|||_td|jjdS)zStart the Cartesia TTS service. Args: frame: The start frame containing initialization parameters. Nz)Initialized NvidiaTTSService with model: ) r=startr_rfrDr debugr&r5)rErgrHrrrhs  zNvidiaTTSService.starttext context_idc sdttjddfffdd }dddttjffdd }zPjdus+Jd jdus4Jd td d t |IdH}||2z3dHW} IdHt |j j d |d}|VqK6IdHWdStjy}ztdtd|dVWYd}~dSd}~wty}ztd|td|dVWYd}~dSd}~ww)aGenerate speech from text using NVIDIA Riva TTS. Args: text: The text to synthesize into speech. context_id: The context ID for tracking audio frames. Yields: Frame: Audio frames containing the synthesized speech data. rTNc s,jjjjjjjdjjid}|S)N)sample_rate_hzzero_shot_audio_prompt_filezero_shot_qualitycustom_dictionary)rCsynthesize_onliner&r6r'r/r) responses)rErjrrread_audio_responsess z6NvidiaTTSService.run_tts..read_audio_responsescSs zt|WStyYdSwr)next StopIteration)itrrr async_nexts   z,NvidiaTTSService.run_tts..async_nextcs* t|IdH}|durdS|Vqr)asyncio to_thread)iteratoritem)rvrrasync_iteratorsz0NvidiaTTSService.run_tts..async_iteratorzTTS service not initializedz#Synthesis configuration not createdz: Generating TTS [])audior/ num_channelsrkz# timeout waiting for audio responsez error: )errorz exception: )rrttsSynthesizeSpeechResponserrCrDr rirwrxstop_ttfb_metricsrr~r/start_tts_usage_metrics TimeoutErrorrr Exception) rErjrkrrr{rqresprger)rvrErjrrun_ttss:   $$zNvidiaTTSService.run_tts)rr r!r"rr9r$rr*strr r#rboolr>rRdictrrUr_rfrrhr rrr __classcell__rrrHrr%8sL     P    (r%).r"rwos dataclassesrrtypingrrrrrr (pipecat.utils.tracing.service_decoratorsr environlogurur pydanticrpipecat.frames.framesrrrrpipecat.services.settingsrrrpipecat.services.tts_servicerpipecat.transcriptions.languager riva.clientrYriva.client.proto.riva_tts_pb2rZrbrcrModuleNotFoundErrorrrrrr%rrrrs2