o qmi6@sddlZddlZddlZddlmmZddlmZm Z ddl m Z ddl m Z ddlmZddlmZddlmZdd lmZdd lmZdd lmZdd lmZdd lmZeje eefZGdddeZ GdddeZ!dS)N)EventEmitterMixin EventType) parse_obj_as) AudioOutput) FlushSignal) ErrorResponse) EventResponse)ConfigureConnection)ConfigureConnectionData) PingSignal)SendText) SendTextDataceZdZdejffdd ZddZddZ    d.dedede de de de de dedede de ddfddZ d eddfd!d"Z d/d#d$Zd/d%d&Zdefd'd(Zd)ejddfd*d+Zd)ejddfd,d-ZZS)0&AsyncTextToSpeechStreamingSocketClient websocketct||_dSNsuper__init__ _websocketselfr __class__c/home/ubuntu/.local/lib/python3.10/site-packages/sarvamai/text_to_speech_streaming/socket_client.pyr  z/AsyncTextToSpeechStreamingSocketClient.__init__cCs@|j2z3dHW}t|trt|n|}tt|Vq6dSrr isinstancestrjsonloadsr)TextToSpeechStreamingSocketClientResponsermessagerrr __aiter__s z0AsyncTextToSpeechStreamingSocketClient.__aiter__c s|tjdzTz%|j2z3dHW}t|trt|n|}tt |}|tj |q 6Wnt j yH}z |tj |WYd}~nd}~wwW|tjddSW|tjddS|tjdwaH Start listening for messages on the websocket connection. Emits events in the following order: - EventType.OPEN when connection is established - EventType.MESSAGE for each message received - EventType.ERROR if an error occurs - EventType.CLOSE when connection is closed N_emitrOPENrr r!r"r#rr$MESSAGE websocketsWebSocketExceptionERRORCLOSEr raw_messageparsedexcrrrstart_listening!s&    "z6AsyncTextToSpeechStreamingSocketClient.start_listeninganushka?"VFmp3128k2target_language_codespeakerpitchpaceloudnessspeech_sample_rateenable_preprocessingoutput_audio_codecoutput_audio_bitratemin_buffer_sizemax_chunk_lengthreturnNc  s>t||||||||| | | d } t| d} || IdHdSa Configuration message required as the first message after establishing the WebSocket connection. This initializes TTS parameters and can be updated at any time during the WebSocket lifecycle by sending a new config message. When a config update is sent, any text currently in the buffer will be automatically flushed and processed before applying the new configuration. :param target_language_code: The language of the text is BCP-47 format :param speaker: The speaker voice to be used for the output audio. Default: Anushka. Model Compatibility (bulbul:v2): Female: Anushka, Manisha, Vidya, Arya; Male: Abhilash, Karun, Hitesh :param pitch: Controls the pitch of the audio. Lower values result in a deeper voice, while higher values make it sharper. The suitable range is between -0.75 and 0.75. Default is 0.0. :param pace: Controls the speed of the audio. Lower values result in slower speech, while higher values make it faster. The suitable range is between 0.5 and 2.0. Default is 1.0. :param loudness: Controls the loudness of the audio. Lower values result in quieter audio, while higher values make it louder. The suitable range is between 0.3 and 3.0. Default is 1.0. :param speech_sample_rate: Specifies the sample rate of the output audio. Supported values are 8000, 16000, 22050, 24000 Hz. If not provided, the default is 22050 Hz. :param enable_preprocessing: Controls whether normalization of English words and numeric entities (e.g., numbers, dates) is performed. Set to true for better handling of mixed-language text. Default is false. :param output_audio_codec: Audio codec (currently supports MP3 only, optimized for real-time playback) :param output_audio_bitrate: Audio bitrate (choose from 5 supported bitrate options) :param min_buffer_size: Minimum character length that triggers buffer flushing for TTS model processing :param max_chunk_length: Maximum length for sentence splitting (adjust based on content length) ) r>r?r@rArBrCrDrErFrGrHdataNr r _send_modelrr>r?r@rArBrCrDrErFrGrHrLr&rrr configure:s + z0AsyncTextToSpeechStreamingSocketClient.configuretextcs*t|d}t|d}||IdHdSaC Send text to be converted to speech. Text length should be 1-2500 characters. Recommended: <500 characters for optimal streaming performance. Real-time endpoints perform better with longer character counts. :param text: Text to be synthesized (1-2500 characters, recommended <500) )rQrKNrr rNrrQrLr&rrrconvertus  z.AsyncTextToSpeechStreamingSocketClient.convertct}||IdHdSz Forces the text buffer to process immediately, regardless of the min_buffer_size threshold. Use this when you need to process remaining text that hasn't reached the minimum buffer size. NrrNr%rrrflushz,AsyncTextToSpeechStreamingSocketClient.flushcrVz Send ping signal to keep the WebSocket connection alive. The connection automatically closes after one minute of inactivity. Nr rNr%rrrpingrZz+AsyncTextToSpeechStreamingSocketClient.pingcs4|jIdH}t|trt|n|}tt|S)B Receive a message from the websocket connection. Nrrecvr r!r"r#rr$rrLrrrr`s z+AsyncTextToSpeechStreamingSocketClient.recvrLcs,t|tr t|}|j|IdHdSz= Send a message to the websocket connection. Nr dictr"dumpsrsendrarrr_sends  z,AsyncTextToSpeechStreamingSocketClient._sendcs||IdHdSzD Send a Pydantic model to the websocket connection. NrgrdrarrrrNsz2AsyncTextToSpeechStreamingSocketClient._send_model r6r7r8r8r9Fr:r;r<r=rIN)__name__ __module__ __qualname__r-WebSocketClientProtocolrr'r5r!floatintboolrPrUrYr]r$r`typingAnyrgrN __classcell__rrrrrZ     ; rcr)0!TextToSpeechStreamingSocketClientrcrrrrrrrrrz*TextToSpeechStreamingSocketClient.__init__ccs6|jD]}t|trt|n|}tt|VqdSrrr%rrr__iter__s  z*TextToSpeechStreamingSocketClient.__iter__c Cs|tjdzOz |jD]}t|trt|n|}tt |}|tj |q Wnt j yB}z |tj |WYd}~nd}~wwW|tjddSW|tjddS|tjdwr(r)r1rrrr5s$     "z1TextToSpeechStreamingSocketClient.start_listeningr6r7r8r9Fr:r;r<r=r>r?r@rArBrCrDrErFrGrHrINc  Cs6t||||||||| | | d } t| d} || dSrJrMrOrrrrPs+ z+TextToSpeechStreamingSocketClient.configurerQcCs"t|d}t|d}||dSrRrSrTrrrrUs  z)TextToSpeechStreamingSocketClient.convertcCt}||dSrWrXr%rrrrYz'TextToSpeechStreamingSocketClient.flushcCryr[r\r%rrrr]rzz&TextToSpeechStreamingSocketClient.pingcCs,|j}t|trt|n|}tt|S)r^r_rarrrr`"s  z&TextToSpeechStreamingSocketClient.recvrLcCs$t|tr t|}|j|dSrbrcrarrrrg*s  z'TextToSpeechStreamingSocketClient._sendcCs||dSrhrirarrrrN2sz-TextToSpeechStreamingSocketClient._send_modelrjrk)rlrmrnwebsockets_sync_connection Connectionrrxr5r!rprqrrrPrUrYr]r$r`rsrtrgrNrurrrrrwrvrw)"r"rsr-websockets.sync.connectionsync connectionr{ core.eventsrrcore.pydantic_utilitiesrtypes.audio_outputrtypes.flush_signalrtypes.error_responsertypes.event_responser types.configure_connectionr types.configure_connection_datar types.ping_signalr types.send_textr types.send_text_datarUnionr$rrwrrrrs&