o i5@sdZddlZddlZddlmZddlmZmZmZddl m Z ddl m Z m Z mZmZmZmZmZmZmZmZddlmZddlmZdd lmZdd lmZdd lmZeGd d d eZ GdddeZ!dS)a/Deepgram text-to-speech service for AWS SageMaker. This module provides a Pipecat TTS service that connects to Deepgram models deployed on AWS SageMaker endpoints. Uses HTTP/2 bidirectional streaming for low-latency real-time speech synthesis with support for interruptions and streaming audio output. N) dataclass)AnyAsyncGeneratorOptional)logger) BotStoppedSpeakingFrame CancelFrameEndFrame ErrorFrameFrameInterruptionFrameLLMFullResponseEndFrame StartFrameTTSAudioRawFrameTTSStartedFrame)FrameDirection)SageMakerBidiClient) TTSSettings) TTSService) traced_ttsc@seZdZdZdS)DeepgramSageMakerTTSSettingsz)Settings for DeepgramSageMakerTTSService.N)__name__ __module__ __qualname____doc__rr[/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/deepgram/sagemaker/tts.pyr)srcs<eZdZUdZeZeed<ddddddededeed ee d ed eef fd d Z de fddZ de ffdd Zdeffdd Zdeffdd Zdedeffdd ZddZddZdedeeefffd d! Zd"d#Zdedeffd$d% Zd,d&eefd'd(Ze d)ed&ede!edffd*d+Z"Z#S)-DeepgramSageMakerTTSServicea@Deepgram text-to-speech service for AWS SageMaker. Provides real-time speech synthesis using Deepgram models deployed on AWS SageMaker endpoints. Uses HTTP/2 bidirectional streaming for low-latency audio generation with support for interruptions via the Clear message. Requirements: - AWS credentials configured (via environment variables, AWS CLI, or instance metadata) - A deployed SageMaker endpoint with Deepgram TTS model: https://developers.deepgram.com/docs/deploy-amazon-sagemaker - ``pipecat-ai[sagemaker]`` installed Example:: tts = DeepgramSageMakerTTSService( endpoint_name="my-deepgram-tts-endpoint", region="us-east-2", settings=DeepgramSageMakerTTSService.Settings( voice="aura-2-helena-en", ) ) _settingsNlinear16)voice sample_rateencodingsettings endpoint_nameregionr r!r"r#c  s|dur |dd|p d}|jd|dd}|dur||tjd|ddd|d|||_||_||_d|_d|_ d|_ d|_ dS) aInitialize the Deepgram SageMaker TTS service. Args: endpoint_name: Name of the SageMaker endpoint with Deepgram TTS model deployed (e.g., "my-deepgram-tts-endpoint"). region: AWS region where the endpoint is deployed (e.g., "us-east-2"). voice: Voice model to use for synthesis. Defaults to "aura-2-helena-en". .. deprecated:: 0.0.105 Use ``settings=DeepgramSageMakerTTSService.Settings(voice=...)`` instead. sample_rate: Audio sample rate in Hz. If None, uses the value from StartFrame. encoding: Audio encoding format. Defaults to "linear16". settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional arguments passed to the parent TTSService. Nr zaura-2-helena-en)modelr languageT)r!push_stop_framespause_frame_processingappend_trailing_spacer#Fr) "_warn_init_param_moved_to_settingsSettings apply_updatesuper__init___endpoint_name_region _encoding_client_response_task _context_id _ttfb_started) selfr$r%r r!r"r#kwargsdefault_settings __class__rrr/Ks4    z$DeepgramSageMakerTTSService.__init__returncCsdS)zCheck if this service can generate processing metrics. Returns: True, as Deepgram SageMaker TTS service supports metrics generation. Tr)r7rrrcan_generate_metricssz0DeepgramSageMakerTTSService.can_generate_metricsframec&t|IdH|IdHdS)zStart the Deepgram SageMaker TTS service. Args: frame: The start frame containing initialization parameters. N)r.start_connectr7r>r:rrr@z!DeepgramSageMakerTTSService.startcr?)zbStop the Deepgram SageMaker TTS service. Args: frame: The end frame. N)r.stop _disconnectrBr:rrrDrCz DeepgramSageMakerTTSService.stopcr?)zgCancel the Deepgram SageMaker TTS service. Args: frame: The cancel frame. N)r.cancelrErBr:rrrFrCz"DeepgramSageMakerTTSService.cancel directioncsNt||IdHt|ttfr|IdHdSt|tr%d|_dSdS)zProcess frames with special handling for LLM response end. Args: frame: The frame to process. direction: The direction of frame processing. NF)r. process_frame isinstancer r flush_audiorr6)r7r>rGr:rrrHs  z)DeepgramSageMakerTTSService.process_framec stdd|jjd|jd|j}t|j|jd|d|_ z |j IdH| | |_ td|d IdHWdStyk}z|jd ||d IdH|d t|IdHWYd}~dSd}~ww) zConnect to the SageMaker endpoint and start the BiDi session. Builds the Deepgram TTS query string, creates the BiDi client, starts the streaming session, and launches a background task for processing responses. z*Connecting to Deepgram TTS on SageMaker...zmodel=z &encoding=z &sample_rate=zv1/speak)r$r%model_invocation_pathmodel_query_stringNz&Connected to Deepgram TTS on SageMaker on_connectedUnknown error occurred:  error_msg exceptionon_connection_error)rdebugrr r2r!rr0r1r3 start_session create_task_process_responsesr4_call_event_handler Exception push_errorstr)r7 query_stringerrrrAs(  $z$DeepgramSageMakerTTSService._connectc s|jr]|jjr_tdz |jddiIdHWnty4}ztd|WYd}~nd}~ww|jrF|jsF| |jIdH|j IdHtd| dIdHdSdSdS)zDisconnect from the SageMaker endpoint. Sends a Close message to Deepgram, cancels the response processing task, and closes the BiDi session. Safe to call multiple times. z/Disconnecting from Deepgram TTS on SageMaker...typeCloseNzFailed to send Close message: z+Disconnected from Deepgram TTS on SageMakeron_disconnected) r3 is_activerrS send_jsonrXwarningr4done cancel_task close_sessionrW)r7r\rrrrEs  z'DeepgramSageMakerTTSService._disconnectdeltacsFt|IdH}|s|Sd|vr|jj|j_||||S)zApply a settings delta and reconnect if necessary. Since all settings are part of the SageMaker session query string, any setting change requires reconnecting to apply the new values. Nr )r._update_settingsrr r&_sync_model_name_to_metrics _warn_unhandled_updated_settings)r7rfchangedr:rrrgs  z,DeepgramSageMakerTTSService._update_settingsc szz|jr|jjr|jIdH}|durnt|drt|jdr|jjr|jj}zS|d}t|}| d}|dkrGt d|n5|dkrTt d |n(|d krat d |n|d krtt |d | ddnt d|Wn%ttjfy|IdHt||jd|jd}||IdHYnw|jr|jjs Wn-tjyt dYn'ty}z|jd||dIdHWYd}~nd}~wwWt ddSWt ddSWt ddSt dw)ahProcess streaming responses from Deepgram TTS on SageMaker. Continuously receives responses from the BiDi stream. Attempts to decode each payload as UTF-8 JSON for control messages (Flushed, Cleared, Metadata, Warning). If decoding fails, treats the payload as raw audio bytes and pushes a TTSAudioRawFrame downstream. Nvaluebytes_zutf-8r]MetadatazReceived metadata: FlushedzReceived Flushed: ClearedzReceived Cleared: Warningz warning: descriptionzUnknown warningzReceived unknown message type:  context_idz TTS response processor cancelledrNrOzTTS response processor stopped)r3r`receive_responsehasattrrkrldecodejsonloadsgetrtracerbrSUnicodeDecodeErrorJSONDecodeErrorstop_ttfb_metricsrr!r5 push_frameasyncioCancelledErrorrXrY)r7resultpayload response_dataparsedmsg_typer>r\rrrrVsf    )&z.DeepgramSageMakerTTSService._process_responsesc st||IdHd|_|jrA|jjrCz|jddiIdHWdSty@}zt|d|WYd}~dSd}~wwdSdS)zHandle interruption by sending Clear message to Deepgram. The Clear message will clear Deepgram's internal text buffer and stop sending audio, allowing for a new response to be generated. NFr]Clearz error sending Clear message: ) r._handle_interruptionr6r3r`rarXrerror)r7r>rGr\r:rrr?s"z0DeepgramSageMakerTTSService._handle_interruptionrtc sp|jr4|jjr6z|jddiIdHWdSty3}zt|d|WYd}~dSd}~wwdSdS)zFlush any pending audio synthesis by sending Flush command. This should be called when the LLM finishes a complete response to force generation of audio from Deepgram's internal text buffer. r]FlushNz error sending Flush message: )r3r`rarXrr)r7rtr\rrrrJNs"z'DeepgramSageMakerTTSService.flush_audiotextc Cst|d|dz5||s-||IdH|js'|IdHd|_t|dV||_|j d|dIdHdVWdSt y]}zt d|d VWYd}~dSd}~ww) aNGenerate speech from text using Deepgram TTS on SageMaker. Args: text: The text to synthesize into speech. context_id: The context ID for tracking audio frames. Yields: Frame: TTSStartedFrame, then None (audio comes asynchronously via the response processor). z: Generating TTS []NTrsSpeak)r]rrN)r) rrSaudio_context_availablecreate_audio_contextr6start_ttfb_metricsrr5r3rarXr )r7rrtr\rrrrun_ttsZs      z#DeepgramSageMakerTTSService.run_tts)N)$rrrrrr,__annotations__rZrintr/boolr=rr@r rDrrFr rrHrArErdictrrgrVr rrJrrr __classcell__rrr:rr0sD ;    9 (r)"rrrx dataclassesrtypingrrrlogururpipecat.frames.framesrrr r r r r rrr"pipecat.processors.frame_processorr*pipecat.services.aws.sagemaker.bidi_clientrpipecat.services.settingsrpipecat.services.tts_servicer(pipecat.utils.tracing.service_decoratorsrrrrrrrs  0