o i7` @s|dZddlZddlZddlZddlmZddlmZmZm Z ddl Z ddl m Z ddl mZddlmZmZmZmZmZmZmZddlmZdd lmZdd lmZmZmZdd lm Z m!Z!dd l"m#Z#zddl$Z$dd l%m&Z'ddl(m)Z)Wn e*yZ+ze ,de+e ,de-de+dZ+[+wwde de e.fddZ/eGdddeZ0GdddeZ1GdddeZ2dS)z-Async text-to-speech service implementations.N) dataclass)AnyAsyncGeneratorOptional)logger) BaseModel) CancelFrameEndFrame ErrorFrameFrame StartFrameTTSAudioRawFrameTTSStoppedFrame)FrameDirection) TTSSettings)TextAggregationMode TTSServiceWebsocketTTSService)Languageresolve_language) traced_tts)connect)Statez Exception: zEIn order to use Async, you need to `pip install pipecat-ai[asyncai]`.zMissing module: languagereturncCsitjdtjdtjdtjdtjdtjdtjdtjdtj d tj d tj d tj d tj d tjdtjdtjd}t||ddS)zConvert a Language enum to Async language code. Args: language: The Language enum value to convert. Returns: The corresponding Async language code, or None if not supported. enfresdeitptnlarrurojahehytrhizhT) use_base_code)rENFRESDEITPTNLARRUROJAHEHYTRHIZHr)r LANGUAGE_MAPr=P/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/asyncai/tts.pylanguage_to_async_language,sD      r?c@seZdZdZdS)AsyncAITTSSettingsz9Settings for AsyncAITTSService and AsyncAIHttpTTSService.N)__name__ __module__ __qualname____doc__r=r=r=r>r@Ksr@cseZdZUdZeZeed<GdddeZddddddd ddddd d e d e e d e de de e de e de de de ede ede e de e ffddZdedee efffdd Zde fddZdede e fd d!ZdKd$e d%e d&e de fd'd(Zd)effd*d+ Zd)effd,d- Zd)effd.d/ Zfd0d1Zfd2d3Zd4d5Zd6d7Z d8d9Z!dLd%e e fd:d;Z"e#j$fd)e%d Z&d?d@Z'dAdBZ(d%e fdCdDZ)d%e fdEdFZ*d%e fdGdHZ+e,d$e d%e de-e%dffdIdJZ.Z/S)MAsyncAITTSServiceztAsync TTS service with WebSocket streaming. Provides text-to-speech using Async's streaming WebSocket API. _settingsc@"eZdZUdZdZeeed<dS)zAsyncAITTSService.InputParamsaInput parameters for Async TTS configuration. .. deprecated:: 0.0.105 Use ``AsyncAITTSService.Settings`` directly via the ``settings`` parameter instead. Parameters: language: Language to use for synthesis. NrrArBrCrDrrr__annotations__r=r=r=r> InputParams[  rJNv1z/wss://api.async.com/text_to_speech/websocket/ws pcm_s16leraw) voice_idversionurlmodel sample_rateencoding containerparamssettingsaggregate_sentencestext_aggregation_modeapi_keyrOrPrQrRrSrTrUrVrWrXrYc  s|jdddd}|dur|dd||_|dur"|dd||_| dur1|d| s1| j|_| dur:|| tjd | | d|dd|d | ||_||_ ||_ ||_ ||_ d |_ d|_d|_dS) aInitialize the Async TTS service. Args: api_key: Async API key. voice_id: UUID of the voice to use for synthesis. See docs for a full list: https://docs.async.com/list-voices-16699698e0 .. deprecated:: 0.0.105 Use ``settings=AsyncAITTSService.Settings(voice=...)`` instead. version: Async API version. url: WebSocket URL for Async TTS API. model: TTS model to use (e.g., "async_flash_v1.0"). .. deprecated:: 0.0.105 Use ``settings=AsyncAITTSService.Settings(model=...)`` instead. sample_rate: Audio sample rate. encoding: Audio encoding format. container: Audio container format. params: Additional input parameters for voice customization. .. deprecated:: 0.0.105 Use ``settings=AsyncAITTSService.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 the parent service. async_flash_v1.0NrRvoicerrOr]rRrVT)rXrYpause_frame_processingrSpush_start_framepush_stop_framesrWrr=)Settings"_warn_init_param_moved_to_settingsr]rRr apply_updatesuper__init___api_key _api_version_url_output_container_output_encoding_output_sample_rate _receive_task_keepalive_task)selfrZrOrPrQrRrSrTrUrVrWrXrYkwargsdefault_settings __class__r=r>regsH5      zAsyncAITTSService.__init__deltarcs*t|IdH}|s|S|||S)zgApply a settings delta. Settings are stored but not applied to the active connection. N)rd_update_settings _warn_unhandled_updated_settings)rnrschangedrqr=r>rts  z"AsyncAITTSService._update_settingscCdS)zCheck if this service can generate processing metrics. Returns: True, as Async service supports metrics generation. Tr=rnr=r=r>can_generate_metricsz&AsyncAITTSService.can_generate_metricsrcCt|SzConvert a Language enum to Async language format. Args: language: The language to convert. Returns: The Async-specific language code, or None if not supported. r?rnrr=r=r>language_to_service_language z.AsyncAITTSService.language_to_service_languageFtext context_idforcecCs|||d}t|S)N) transcriptrr)jsondumps)rnrrrmsgr=r=r> _build_msgs  zAsyncAITTSService._build_msgframecs.t|IdH|j|_|IdHdS)z}Start the Async TTS service. Args: frame: The start frame containing initialization parameters. N)rdstartrSrk_connectrnrrqr=r>rszAsyncAITTSService.startc&t|IdH|IdHdS)zUStop the Async TTS service. Args: frame: The end frame. N)rdstop _disconnectrrqr=r>rzAsyncAITTSService.stopcr)zZCancel the Async TTS service. Args: frame: The cancel frame. N)rdcancelrrrqr=r>rrzAsyncAITTSService.cancelcshtIdH|IdH|jr |js |||j|_|jr0|js2|| |_dSdSdSN) rdr_connect_websocket _websocketrl create_task_receive_task_handler _report_errorrm_keepalive_task_handlerrxrqr=r>r s  zAsyncAITTSService._connectcs`tIdH|jr||jIdHd|_|jr'||jIdHd|_|IdHdSr)rdrrl cancel_taskrm_disconnect_websocketrxrqr=r>rszAsyncAITTSService._disconnectc szT|jr|jjtjurWdStdt|jd|jd|j IdH|_|j j d|j j d|j |j|jd|j jd}|t|IdH|dIdHWdSty}z!|jd ||d IdHd|_|d |IdHWYd}~dSd}~ww) NzConnecting to Asyncz ?api_key=z &version=idmoderrUrTrS)model_idr] output_formatr on_connectedUnknown error occurred:  error_msg exceptionon_connection_error)rstaterOPENrdebugwebsocket_connectrhrfrgrFrRr]rirjrkr_get_websocketsendrr_call_event_handler Exception push_error)rninit_msger=r=r>r$s0    "z$AsyncAITTSService._connect_websocketc szzz0|IdH|jr1td|r$|jtddiIdH|jIdHtdWnt yQ}z|j d||dIdHWYd}~nd}~wwWd|_| IdH| dIdHdSWd|_| IdH| dIdHdSd|_| IdH| dIdHw)NzDisconnecting from Async terminateTzDisconnected from Asyncrron_disconnected) stop_all_metricsrrrhas_active_audio_contextrrrcloserrremove_active_audio_contextr)rnrr=r=r>r?s2  &z'AsyncAITTSService._disconnect_websocketcCs|jr|jStd)NzWebsocket not connected)rrrxr=r=r>rQsz AsyncAITTSService._get_websocketcsR|p|}|r |jsdSt|d|jd|dd}|j|IdHdS)zFlush any pending audio. Args: context_id: The specific context to flush. If None, falls back to the currently active context. Nz: flushing audio T)rrr)get_active_audio_context_idrrtracerr)rnrflush_idrr=r=r> flush_audioVs  zAsyncAITTSService.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)rd push_frame)rnrrrqr=r>rdszAsyncAITTSService.push_framecs|2zm3dHW}t|}|sq|d}|ddur(td|q||sM||krDtd|| |IdHn td|q|drr| IdHt |d}t ||jd|d }|||IdHq6dS) NrfinalTz#Received final message for context z4Received a delayed message, recreating the context: z+Ignoring message from unavailable context: audior)rrloadsgetrraudio_context_availablerrcreate_audio_contextstop_ttfb_metricsbase64 b64decoder rSappend_to_audio_context)rnmessagerreceived_ctx_idrrr=r=r>_receive_messagesms0     z#AsyncAITTSService._receive_messagesc sd} t|IdHz2|jr=|jjtjur=|}|r(d|d}tdn ddi}td|j t |IdHWnt j y\}zt|d |WYd}~dSd}~wwq) zBSend periodic keepalive messages to maintain WebSocket connection. TNr)rrzSending keepalive messagerz!Sending keepalive without contextz keepalive error: )asynciosleeprrrrrrrrrr websocketsConnectionClosedwarning)rnKEEPALIVE_SLEEPrkeepalive_messagerr=r=r>rs,  z)AsyncAITTSService._keepalive_task_handlerc s||r:|jr_close_contexts (z AsyncAITTSService._close_contextc||IdHdS)z7Close the Async AI context when the bot is interrupted.Nrrnrr=r=r>on_audio_context_interruptedsz.AsyncAITTSService.on_audio_context_interruptedcr)aClose the Async AI context after all audio has been played. Async AI does not send a server-side signal when a context is exhausted, so Pipecat must explicitly close it with ``close_context: True`` to free server-side resources. Nrrr=r=r>on_audio_context_completedsz,AsyncAITTSService.on_audio_context_completedc Cst|d|dzW|jr|jjtjur|IdHz|j|d|d}| |IdH| |IdHWn#t y]}zt d|dVt |dVWYd}~WdSd}~wwdVWdSt y}zt d|dVWYd}~dSd}~ww) a!Generate speech from text using Async API websocket endpoint. 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. : Generating TTS []NT)rrrr)rr)rrrrrCLOSEDrrrrstart_tts_usage_metricsrr r)rnrrrrr=r=r>run_ttss(    zAsyncAITTSService.run_tts)rrFr)0rArBrCrDr@rarIrrJstrrintboolrrerdictrrtryrrrr rr rrrrrrrrrr DOWNSTREAMr rrrrrrrrr __classcell__r=r=rqr>rERs|      d     "  (rEcseZdZUdZeZeed<GdddeZddddddd ddd d e d e e d e j de e de de de e de de de ede effddZdefddZdede e fddZdeffdd Zed!e d"e deedffd#d$ZZS)%AsyncAIHttpTTSServicezHTTP-based Async TTS service. Provides text-to-speech using Async's HTTP streaming API for simpler, non-WebSocket integration. Suitable for use cases where streaming WebSocket connection is not required or desired. rFc@rG)z!AsyncAIHttpTTSService.InputParamszInput parameters for Async API. .. deprecated:: 0.0.105 Use ``AsyncAIHttpTTSService.Settings`` directly via the ``settings`` parameter instead. Parameters: language: Language to use for synthesis. NrrHr=r=r=r>rJrKrJNzhttps://api.async.comrLrMrN) rOrRrQrPrSrTrUrVrWrZrOaiohttp_sessionrRrQrPrSrTrUrVrWc  s|jdddd} |dur|dd|| _|dur"|dd|| _| dur1|d| s1| j| _| dur:| | tjd |dd| d | ||_||_ ||_ | |_ ||_ d |_ ||_dS) aInitialize the Async TTS service. Args: api_key: Async API key. voice_id: ID of the voice to use for synthesis. .. deprecated:: 0.0.105 Use ``settings=AsyncAIHttpTTSService.Settings(voice=...)`` instead. aiohttp_session: An aiohttp session for making HTTP requests. model: TTS model to use (e.g., "async_flash_v1.0"). .. deprecated:: 0.0.105 Use ``settings=AsyncAIHttpTTSService.Settings(model=...)`` instead. url: Base URL for Async API. version: API version string for Async API. sample_rate: Audio sample rate. encoding: Audio encoding format. container: Audio container format. params: Additional input parameters for voice customization. .. deprecated:: 0.0.105 Use ``settings=AsyncAIHttpTTSService.Settings(...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional arguments passed to the parent TTSService. r[Nr\rOr]rRrVT)rSr_r`rWrr=)rarbr]rRrrcrdrerf _base_urlrgrirjrk_session)rnrZrOrrRrQrPrSrTrUrVrWrorprqr=r>res@.     zAsyncAIHttpTTSService.__init__rcCrw)zCheck if this service can generate processing metrics. Returns: True, as Async HTTP service supports metrics generation. Tr=rxr=r=r>ryOrzz*AsyncAIHttpTTSService.can_generate_metricsrcCr{r|r}r~r=r=r>rWrz2AsyncAIHttpTTSService.language_to_service_languagercs t|IdH|j|_dS)zStart the Async HTTP TTS service. Args: frame: The start frame containing initialization parameters. N)rdrrSrkrrqr=r>rbs zAsyncAIHttpTTSService.startrrc Cst|d|dzzd|jjd}|jj|||j|j|jd|jjd}|j |j dd}|j d }|j j |||d 4Id HR}|jd krg|Id H}|jd |dId Htd|jd|t} |jd2z3d HW} | syqp|Id H| | qp6t| } Wd Id Hn 1Id HswY||Id Ht| |jd|d} | VWnty} z|jd| | dId HWYd } ~ nd } ~ wwW|Id Hd SW|Id Hd S|Id Hw)aGenerate speech from text using Async's HTTP 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. rrrrr)rrr]rrzapplication/json)rPz x-api-keyz Content-Typez/text_to_speech/streaming)rheadersNzAsync API error: )rzAsync API returned status rir)rrS num_channelsrrr)rrrFr]rRrirjrkrrgrfrrpoststatusrrr bytearraycontent iter_chunkedrextendbytesrr rS)rnrr voice_configpayloadrrQresponse error_textbufferchunk audio_datarrr=r=r>rks`      ( &"zAsyncAIHttpTTSService.run_tts)rArBrCrDr@rarIrrJrraiohttp ClientSessionrrerryrrr rrrr rrr=r=rqr>rsT      Y  (r)3rDrrr dataclassesrtypingrrrrlogururpydanticrpipecat.frames.framesrr r r r r r"pipecat.processors.frame_processorrpipecat.services.settingsrpipecat.services.tts_servicerrrpipecat.transcriptions.languagerr(pipecat.utils.tracing.service_decoratorsrrwebsockets.asyncio.clientrrwebsockets.protocolrModuleNotFoundErrorrrrrr?r@rErr=r=r=r>sB   $