o iG\ @sdZddlZddlZddlZddlmZmZddlmZm Z m Z ddl Z ddl m Z ddlmZddlmZmZmZmZmZmZmZmZmZmZddlmZdd lmZmZm Z dd l!m"Z"m#Z#m$Z$dd l%m&Z&m'Z'dd l(m)Z)zdd l*m+Z,ddl-m.Z.Wn e/yZ0ze 1de0e 1de2de0dZ0[0wwde&de e3fddZ4eGdddeZ5Gddde"Z6Gddde$Z7dS)zNeuphonic text-to-speech service implementations. This module provides WebSocket and HTTP-based integrations with Neuphonic's text-to-speech API for real-time audio synthesis. N) dataclassfield)AnyAsyncGeneratorOptional)logger) BaseModel) BotStoppedSpeakingFrame CancelFrameEndFrame ErrorFrameFrameLLMFullResponseEndFrame StartFrameTTSAudioRawFrame TTSSpeakFrameTTSStoppedFrame)FrameDirection) NOT_GIVEN TTSSettings _NotGiven)InterruptibleTTSServiceTextAggregationMode TTSService)Languageresolve_language) traced_tts)connect)Statez Exception: zKIn order to use Neuphonic, you need to `pip install pipecat-ai[neuphonic]`.zMissing module: languagereturncCsNtjdtjdtjdtjdtjdtjdtjdtjdtj d tj d i }t ||d d S) zConvert a Language enum to Neuphonic language code. Args: language: The Language enum value to convert. Returns: The corresponding Neuphonic language code, or None if not supported. deenesnlarfrptruHIzhT) use_base_code) rDEENESNLARFRPTRUr)ZHr)r LANGUAGE_MAPr6R/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/neuphonic/tts.pylanguage_to_neuphonic_lang_code2s  r8c@s,eZdZUdZedddZeeBed<dS)NeuphonicTTSSettingszSettings for NeuphonicTTSService and NeuphonicHttpTTSService. Parameters: speed: Speech speed multiplier. Defaults to 1.0. cCstSN)rr6r6r6r7SszNeuphonicTTSSettings.)default_factoryspeedN) __name__ __module__ __qualname____doc__rr=floatr__annotations__r6r6r6r7r9Ks r9cseZdZUdZeZeed<GdddeZddddddddd d e d e e d e d e e de de ede ede e de e ffddZde fddZdede e fddZdedee efffdd Zdeffdd Zdeffd!d" Zdeffd#d$ Zd@d%e e fd&d'Zejfded(effd)d* Z ded(effd+d, Z!fd-d.Z"fd/d0Z#d1d2Z$d3d4Z%d5d6Z&d7d8Z'd9d:Z(d;e fdd?Z,Z-S)ANeuphonicTTSServicea!Neuphonic real-time text-to-speech service using WebSocket streaming. Provides real-time text-to-speech synthesis using Neuphonic's WebSocket API. Supports interruption handling, keepalive connections, and configurable voice parameters for high-quality speech generation. _settingsc@4eZdZUdZejZeeed<dZ ee ed<dS)zNeuphonicTTSService.InputParamsa8Input parameters for Neuphonic TTS configuration. .. deprecated:: 0.0.105 Use ``settings=NeuphonicTTSService.Settings(...)`` instead. Parameters: language: Language for synthesis. Defaults to English. speed: Speech speed multiplier. Defaults to 1.0. r?r=N r>r?r@rArr-rrrCr=rBr6r6r6r7 InputParamsa  rINzwss://api.neuphonic.com"V pcm_linear)voice_idurl sample_rateencodingparamssettingsaggregate_sentencestext_aggregation_modeapi_keyrMrNrOrPrQrRrSrTc s|jddtjdd} |dur|dd|| _|dur4|d|s4|jdur+|j| _|jdur4|j| _|dur=| |tj d || ddd|| d | ||_ ||_ d|_ d|_ ||_||_dS) aInitialize the Neuphonic TTS service. Args: api_key: Neuphonic API key for authentication. voice_id: ID of the voice to use for synthesis. .. deprecated:: 0.0.105 Use ``settings=NeuphonicTTSService.Settings(voice=...)`` instead. url: WebSocket URL for the Neuphonic API. sample_rate: Audio sample rate in Hz. Defaults to 22050. encoding: Audio encoding format. Defaults to "pcm_linear". params: Additional input parameters for TTS configuration. .. deprecated:: 0.0.105 Use ``settings=NeuphonicTTSService.Settings(...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. aggregate_sentences: Deprecated. Use text_aggregation_mode instead. .. deprecated:: 0.0.104 Use ``text_aggregation_mode`` instead. text_aggregation_mode: How to aggregate text before synthesis. **kwargs: Additional arguments passed to parent InterruptibleTTSService. NrGmodelvoicerr=rMrXrQTg@)rSrTpush_stop_framespush_start_framestop_frame_timeout_srOrRr6)Settingsrr-"_warn_init_param_moved_to_settingsrXrr= apply_updatesuper__init___api_key_url _receive_task_keepalive_task _encoding_sampling_rate) selfrUrMrNrOrPrQrRrSrTkwargsdefault_settings __class__r6r7r`osF*       zNeuphonicTTSService.__init__r cCdS)zCheck if this service can generate processing metrics. Returns: True, as Neuphonic service supports metrics generation. Tr6rgr6r6r7can_generate_metricsz(NeuphonicTTSService.can_generate_metricsrcCt|SzConvert a Language enum to Neuphonic service language format. Args: language: The language to convert. Returns: The Neuphonic-specific language code, or None if not supported. r8rgrr6r6r7language_to_service_language z0NeuphonicTTSService.language_to_service_languagedeltacsLt|IdH}|r$|IdH|IdHtd|jd|S)zN _websocketsendjsondumps)rgrmsgr6r6r7 flush_audios zNeuphonicTTSService.flush_audio directioncst||IdHdS)zPush a frame downstream with special handling for stop conditions. Args: frame: The frame to push. direction: The direction to push the frame. N)r_ push_framergr}rrjr6r7rszNeuphonicTTSService.push_framecsnt||IdHt|tr|IdHdSt|tr'|IdHdSt|tr5|IdHdSdS)zProcess frames with special handling for speech control. Args: frame: The frame to process. direction: The direction of frame processing. N)r_ process_frame isinstancerpause_processing_framesrr resume_processing_framesrrjr6r7r s   z!NeuphonicTTSService.process_framecshtIdH|IdH|jr |js |||j|_|jr0|js2|| |_dSdSdS)z:Connect to Neuphonic WebSocket and start background tasks.N) r_rz_connect_websocketrrc create_task_receive_task_handler _report_errorrd_keepalive_task_handlerrmrjr6r7rzs  zNeuphonicTTSService._connectcs`tIdH|jr||jIdHd|_|jr'||jIdHd|_|IdHdS)z7Disconnect from Neuphonic WebSocket and clean up tasks.N)r_ryrc cancel_taskrd_disconnect_websocketrmrjr6r7ry)szNeuphonicTTSService._disconnectc s4zk|jr|jjtjurWdStd|jj|jj|j |j |jj d}g}| D]\}}|dur<| |d|q*|jd|jj}|rS|dd|7}d|ji}t||d IdH|_|d IdHWdSty}z!|jd ||d IdHd|_|d |IdHWYd}~dSd}~ww)z0Establish WebSocket connection to Neuphonic API.NzConnecting to Neuphonic) lang_coder=rP sampling_raterM=z/speak/?&z x-api-key)additional_headers on_connectedUnknown error occurred:  error_msg exceptionon_connection_error)rstaterOPENrdebugrErr=rerfrXitemsappendrbjoinrawebsocket_connect_call_event_handler Exception push_error)rg tts_config query_paramskeyvaluerNheaderser6r6r7r7s8  "z&NeuphonicTTSService._connect_websocketc szUz|IdH|jrtd|jIdHWnty:}z|jd||dIdHWYd}~nd}~wwWd|_|dIdHdSWd|_|dIdHdSd|_|dIdHw)z.Close WebSocket connection and clean up state.NzDisconnecting from Neuphonicrron_disconnected)stop_all_metricsrrrcloserrr)rgrr6r6r7rZs& &z)NeuphonicTTSService._disconnect_websocketcs|j2z?3dHW}t|trCt|}|drC|ddrC|IdHt|dd}t ||j d| d}| |IdHq6dS)z6Receive and process messages from Neuphonic WebSocket.Ndataaudior) rrstrrloadsgetstop_ttfb_metricsbase64 b64decoderrOget_active_audio_context_idr)rgmessagerrr}r6r6r7_receive_messageshs  z%NeuphonicTTSService._receive_messagescs(d} t|IdH|IdHq)z;Handle keepalive messages to maintain WebSocket connection. TN)asynciosleep_send_keepalive)rgKEEPALIVE_SLEEPr6r6r7rvs z+NeuphonicTTSService._keepalive_task_handlercs0|jrddi}|jt|IdHdSdS)z.Send keepalive message to maintain connection.rNr)rgrr6r6r7r}s z#NeuphonicTTSService._send_keepalivercsF|jr!d|di}td||jt|IdHdSdS)z/Send text to Neuphonic WebSocket for synthesis.rz zSending text to websocket: N)rrrrrr)rgrrr6r6r7 _send_texts zNeuphonicTTSService._send_textc Cstd|dz[|jr|jjtjur|IdHz||IdH||IdHWn1t y_}z%t d|dVt |dV| IdH|IdHWYd}~WdSd}~wwdVWdSt y}zt d|dVWYd}~dSd}~ww)aGenerate speech from text using Neuphonic's streaming API. Args: text: The text to synthesize into speech. context_id: Unique identifier for this TTS context. Yields: Frame: Audio frames containing the synthesized speech. Generating TTS: [rwNrerrorr) rrrrrCLOSEDrzrstart_tts_usage_metricsrr rry)rgrrrr6r6r7run_ttss*    zNeuphonicTTSService.run_ttsr:).r>r?r@rAr9r\rCrrIrrintboolrr`rnrrtrdictrrxrrr rr rrr DOWNSTREAMr rrrzryrrrrrrrrr __classcell__r6r6rjr7rDVsf    U       #(rDcseZdZUdZeZeed<GdddeZddddddd d e d e e d e j d e de e de e de ede effddZdefddZdede e fddZdeffdd Zd&de e fddZd e dedBfd!d"Zed#e de deedffd$d%ZZS)'NeuphonicHttpTTSServiceaNeuphonic text-to-speech service using HTTP streaming. Provides text-to-speech synthesis using Neuphonic's HTTP API with server-sent events for streaming audio delivery. Suitable for applications that prefer HTTP-based communication over WebSocket connections. rEc@rF)z#NeuphonicHttpTTSService.InputParamsaAInput parameters for Neuphonic HTTP TTS configuration. .. deprecated:: 0.0.105 Use ``settings=NeuphonicHttpTTSService.Settings(...)`` instead. Parameters: language: Language for synthesis. Defaults to English. speed: Speech speed multiplier. Defaults to 1.0. rrGr=NrHr6r6r6r7rIrJrINzhttps://api.neuphonic.comrKrL)rMrNrOrPrQrRrUrMaiohttp_sessionrNrOrPrQrRc  s|jddtjdd} |dur|dd|| _|dur4|d|s4|jdur+|j| _|jdur4|j| _|dur=| |tj d |dd| d| ||_ ||_ | d |_ ||_dS) aInitialize the Neuphonic HTTP TTS service. Args: api_key: Neuphonic API key for authentication. voice_id: ID of the voice to use for synthesis. .. deprecated:: 0.0.105 Use ``settings=NeuphonicHttpTTSService.Settings(voice=...)`` instead. aiohttp_session: Shared aiohttp session for HTTP requests. url: Base URL for the Neuphonic HTTP API. sample_rate: Audio sample rate in Hz. Defaults to 22050. encoding: Audio encoding format. Defaults to "pcm_linear". params: Additional input parameters for TTS configuration. .. deprecated:: 0.0.105 Use ``settings=NeuphonicHttpTTSService.Settings(...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional arguments passed to parent TTSService. NrGrVrMrXrQT)rOrYrZrR/r6)r\rr-r]rXrr=r^r_r`ra_sessionrstrip _base_urlre) rgrUrMrrNrOrPrQrRrhrirjr6r7r`s<$       z NeuphonicHttpTTSService.__init__r cCrl)zCheck if this service can generate processing metrics. Returns: True, as Neuphonic HTTP service supports metrics generation. Tr6rmr6r6r7rn roz,NeuphonicHttpTTSService.can_generate_metricsrcCrprqrrrsr6r6r7rtruz4NeuphonicHttpTTSService.language_to_service_languager}cst|IdHdS)zStart the Neuphonic HTTP TTS service. Args: frame: The start frame containing initialization parameters. N)r_rrrjr6r7r szNeuphonicHttpTTSService.startrcsdS)z|Flush any pending audio synthesis. Note: HTTP-based service doesn't require explicit flushing. Nr6)rgrr6r6r7r(sz#NeuphonicHttpTTSService.flush_audiorc Cs|}|r d|vr dSz0|dd\}}|r|dkrWdSt|}|ddur:td|dd d|d|WSttjfyZ}zt d |WYd}~dSd}~ww) zParse a Server-Sent Event message. Args: message: The SSE message to parse. Returns: Parsed message dictionary or None if not a data message. rNz: rz[DONE]errorszNeuphonic API error status_codeunknownzFailed to parse SSE message: ) stripsplitrrrr ValueErrorJSONDecodeErrorrwarning)rgr_ data_content message_dictrr6r6r7_parse_sse_message0s$   z*NeuphonicHttpTTSService._parse_sse_messagerc Cs~td|d|jd|jj}|jdd}||jj|j|j|jjd}|jj r2|jj |d<zz|j j |||d4Id H}|j d krs| Id H}d |j d |}t|d V Wd Id HWW|Id Hd S||Id H|j2zb3d HW} | sq~| jddd} | sq~z2|| } | d ur| didd ur| dd} t| } |Id Ht| |jd|dVWq~ty}ztd|d VWYd }~q~d }~ww6Wd Id Hn 1Id HswYWn*tjytdty"}ztd|d VWYd }~nd }~wwW|Id Hd SW|Id Hd S|Id Hw)a,Generate speech from text using Neuphonic streaming API. Args: text: The text to convert to speech. context_id: Unique identifier for this TTS context. Yields: Frame: Audio frames containing the synthesized speech and status information. rrwz /sse/speak/zapplication/json)z X-API-KEYz Content-Type)rrrPrr=rM)rrNzNeuphonic API error: HTTP z - rzutf-8ignore)rrrrrrzTTS generation cancelled)rrrrErrarerOr=rXrpoststatusrr rrcontentdecoderrrrrrrrCancelledError)rgrrrNrpayloadresponse error_text error_messagelinerparsed_message audio_b64 audio_bytesrr6r6r7rRsx    ,     (& "zNeuphonicHttpTTSService.run_ttsr:)r>r?r@rAr9r\rCrrIrraiohttp ClientSessionrr`rrnrrtrrrrrrrr rrr6r6rjr7rsF   J "(r)8rArrr dataclassesrrtypingrrrrlogururpydanticrpipecat.frames.framesr r r r r rrrrr"pipecat.processors.frame_processorrpipecat.services.settingsrrrpipecat.services.tts_servicerrrpipecat.transcriptions.languagerr(pipecat.utils.tracing.service_decoratorsrwebsockets.asyncio.clientrrwebsockets.protocolrModuleNotFoundErrorrrrrr8r9rDrr6r6r6r7s>  0     V