o iT1 @s8dZddlZddlmZddlmZmZmZddlm Z ddl m Z m Z m Z mZmZmZmZddlmZddlmZdd lmZdd lmZmZdd lmZzdd lmZdd l m!Z!Wn e"y|Z#ze $de#e $de%de#dZ#[#wwdedee&fddZ'eGdddeZ(GdddeZ)dS)z+LMNT text-to-speech service implementation.N) dataclass)AnyAsyncGeneratorOptional)logger) CancelFrameEndFrame ErrorFrameFrame StartFrameTTSAudioRawFrameTTSStoppedFrame)FrameDirection) TTSSettings)InterruptibleTTSService)Languageresolve_language) traced_tts)connect)Statez Exception: zAIn order to use LMNT, you need to `pip install pipecat-ai[lmnt]`.zMissing module: languagereturnc Csitjdtjdtjdtjdtjdtjdtjdtjdtj d tj d tj d tj d tj d tjdtjdtjdtjdtjdtjdtjdtjdi}t||ddS)zConvert a Language enum to LMNT language code. Args: language: The Language enum value to convert. Returns: The corresponding LMNT language code, or None if not supported. ardeenesfrhiiditjakonlplptrusvthtrukurvizhT) use_base_code)rARDEENESFRHIIDITJAKONLPLPTRUSVTHTRUKURVIZHr)r LANGUAGE_MAPrDM/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/lmnt/tts.pylanguage_to_lmnt_language(sR      rFc@seZdZdZdS)LmntTTSSettingszSettings for LmntTTSService.N)__name__ __module__ __qualname____doc__rDrDrDrErGLsrGcspeZdZUdZeZeed<ddejddddde de e de e d ed e d e e d e effd dZ de fddZd ede e fddZdeffdd Zdeffdd Zdeffdd Zejfdedeffdd ZfddZfd d!Zd"edee efffd#d$ Zd%d&Z d'd(Z!d)d*Z"d3d+e e fd,d-Z#d.d/Z$e%d0e d+e de&edffd1d2Z'Z(S)4LmntTTSServicezLMNT real-time text-to-speech service. Provides real-time text-to-speech synthesis using LMNT's WebSocket API. Supports streaming audio generation with configurable voice models and language settings. _settingsN pcm_s16le)voice_id sample_rater output_formatmodelsettingsapi_keyrOrPrrQrRrSc  s|jddtjd} |dur|dd|| _|dur#|dd|| _|dur0|dd|| _|dur9| |tj d ddd|| d |||_ ||_ d|_ dS) aEInitialize the LMNT TTS service. Args: api_key: LMNT API key for authentication. voice_id: ID of the voice to use for synthesis. .. deprecated:: 0.0.105 Use ``settings=LmntTTSService.Settings(voice=...)`` instead. sample_rate: Audio sample rate. If None, uses default. language: Language for synthesis. Defaults to English. .. deprecated:: 0.0.106 Use ``settings=LmntTTSService.Settings(language=...)`` instead. output_format: Audio output format. One of "pcm_s16le", "pcm_f32le", "mp3", "ulaw", "webm". Defaults to "pcm_s16le". model: TTS model to use. .. deprecated:: 0.0.105 Use ``settings=LmntTTSService.Settings(model=...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional arguments passed to parent InterruptibleTTSService. auroraN)rRvoicerrOrVrrRT)push_stop_framespush_start_framepause_frame_processingrPrSrD) Settingsrr0"_warn_init_param_moved_to_settingsrVrrR apply_updatesuper__init___api_key_output_format _receive_task) selfrTrOrPrrQrRrSkwargsdefault_settings __class__rDrEr^^s8'      zLmntTTSService.__init__rcCsdS)zCheck if this service can generate processing metrics. Returns: True, as LMNT service supports metrics generation. TrDrbrDrDrEcan_generate_metricssz#LmntTTSService.can_generate_metricscCst|S)zConvert a Language enum to LMNT service language format. Args: language: The language to convert. Returns: The LMNT-specific language code, or None if not supported. )rF)rbrrDrDrElanguage_to_service_languages z+LmntTTSService.language_to_service_languageframec&t|IdH|IdHdS)z|Start the LMNT TTS service. Args: frame: The start frame containing initialization parameters. N)r]start_connectrbrjrerDrErlzLmntTTSService.startcrk)zTStop the LMNT TTS service. Args: frame: The end frame. N)r]stop _disconnectrnrerDrErprozLmntTTSService.stopcrk)zYCancel the LMNT TTS service. Args: frame: The cancel frame. N)r]cancelrqrnrerDrErrrozLmntTTSService.cancel 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_frame)rbrjrsrerDrErtszLmntTTSService.push_framecsLtIdH|IdH|jr"|js$|||j|_dSdSdS)z1Connect to LMNT WebSocket and start receive task.N)r]rm_connect_websocket _websocketra create_task_receive_task_handler _report_errorrgrerDrErms  zLmntTTSService._connectcsBtIdH|jr||jIdHd|_|IdHdS)z2Disconnect from LMNT WebSocket and clean up tasks.N)r]rqra cancel_task_disconnect_websocketrgrerDrErqs zLmntTTSService._disconnectdeltacs8t|IdH}|r|IdH|IdH|S)zApply a settings delta. Args: delta: A :class:`TTSSettings` (or ``LmntTTSService.Settings``) delta. Returns: Dict mapping changed field names to their previous values. N)r]_update_settingsrqrm)rbr|changedrerDrEr}s  zLmntTTSService._update_settingsc szC|jr|jjtjurWdStd|j|jj|j |j |jj |jj d}t dIdH|_|jt|IdH|dIdHWdStyq}z!|jd||dIdHd|_|d|IdHWYd}~dSd}~ww) zConnect to LMNT websocket.NzConnecting to LMNT)z X-API-KeyrVformatrPrrRz&wss://api.lmnt.com/v1/ai/speech/stream on_connectedUnknown error occurred:  error_msg exceptionon_connection_error)rvstaterOPENrdebugr_rMrVr`rPrrRwebsocket_connectsendjsondumps_call_event_handler Exception push_error)rbinit_msgerDrDrErus*  "z!LmntTTSService._connect_websocketc szUz|IdH|jrtd|jIdHWnty:}z|jd||dIdHWYd}~nd}~wwWd|_|dIdHdSWd|_|dIdHdSd|_|dIdHw)zDisconnect from LMNT websocket.NzDisconnecting from LMNTzError disconnecting from LMNT: ron_disconnected)stop_all_metricsrvrrcloserrr)rbrrDrDrEr{"s& &z$LmntTTSService._disconnect_websocketcCs|jr|jStd)z*Get the WebSocket connection if available.zWebsocket not connected)rvrrgrDrDrE_get_websocket3szLmntTTSService._get_websocket context_idcs<|jr |jjtjur dS|tddiIdHdS)z"Flush any pending audio synthesis.NflushT)rvrrCLOSEDrrrr)rbrrDrDrE flush_audio9s"zLmntTTSService.flush_audioc s|2ze3dHW}t|tr+|IdHt||jd|d}||IdHqz-t |}d|vrW|t IdH| IdH|j d|ddIdHWdSWqtj yjtd|Yqw6dS)z%Receive messages from LMNT websocket.N)audiorP num_channelsrerrorzError: )rzInvalid JSON message: )r isinstancebytesstop_ttfb_metricsr rPget_active_audio_context_idrtrloadsr rrJSONDecodeErrorrr)rbmessagerjmsgrDrDrE_receive_messages?s.  z LmntTTSService._receive_messagestextc Cs4t|d|dzq|jr|jjtjur|IdHz(|t d|iIdH|t ddiIdH| |IdHWn1t yw}z%t d|dVt|d V|IdH|IdHWYd}~WdSd}~wwdVWdSt y}zt d|dVWYd}~dSd}~ww) aGenerate TTS audio from text using LMNT's streaming API. 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. z: Generating TTS []NrrTr)r)r)rrrvrrrrmrrrrstart_tts_usage_metricsrr r rq)rbrrrrDrDrErun_ttsWs,    zLmntTTSService.run_tts)N))rHrIrJrKrGrZ__annotations__rr0strrintr^boolrhrir rlrrprrrr DOWNSTREAMr rtrmrqrdictrr}rur{rrrrrr __classcell__rDrDrerErLSsR  K     (rL)*rKr dataclassesrtypingrrrlogururpipecat.frames.framesrrr r r r r "pipecat.processors.frame_processorrpipecat.services.settingsrpipecat.services.tts_servicerpipecat.transcriptions.languagerr(pipecat.utils.tracing.service_decoratorsrwebsockets.asyncio.clientrrwebsockets.protocolrModuleNotFoundErrorrrrrrFrGrLrDrDrDrEs0  $     $