o i: @sdZddlZddlZddlmZmZddlmZmZm Z m Z m Z ddl Z ddl mZddlmZddlmZmZmZmZmZmZmZmZmZddlmZdd lmZmZm Z dd l!m"Z"m#Z#m$Z$m%Z%dd l&m'Z'm(Z(dd l)m*Z*dd l+m,Z,ddl-m.Z.zddl/m0Z1ddl2m3Z3Wn e4yZ5ze6de5e6de7de5dZ5[5wwde'de8fddZ9eGdddeZ:eGdddeZ;Gddde%ZdS)"zRime text-to-speech service implementations. This module provides both WebSocket and HTTP-based text-to-speech services using Rime's API for streaming and batch audio synthesis. N) dataclassfield)AnyAsyncGeneratorClassVarDictOptional)logger) BaseModel) CancelFrameEndFrame ErrorFrameFrameInterruptionFrame StartFrameTTSAudioRawFrameTTSStartedFrameTTSStoppedFrame)FrameDirection) NOT_GIVEN TTSSettings _NotGiven)InterruptibleTTSServiceTextAggregationMode TTSServiceWebsocketTTSService)Languageresolve_language)BaseTextAggregator)SkipTagsAggregator) traced_tts)connect)Statez Exception: zAIn order to use Rime, you need to `pip install pipecat-ai[rime]`.zMissing module: languagereturnc Cs0tjdtjdtjdtjdtjdi}t||ddS)zConvert pipecat Language to Rime language code. Args: language: The pipecat Language enum value. Returns: Three-letter language code used by Rime (e.g., 'eng' for English). gerfraengspahinF) use_base_code)rDEFRENESHIr)r# LANGUAGE_MAPr1M/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/rime/tts.pylanguage_to_rime_language7s r3c@sxeZdZUdZedddZedBeBed<edddZ e dBeBed<ed ddZ e dBeBed <ed ddZ e dBeBed <ed ddZe dBeBed<edddZe dBeBed<edddZe dBeBed<edddZedBeBed<edddZe dBeBed<edddZe dBeBed<edddZe dBeBed<ddiZeeeefed<dS)RimeTTSSettingsaSettings for RimeTTSService and RimeHttpTTSService. Parameters: segment: Text segmentation mode ("immediate", "bySentence", "never"). speedAlpha: Speech speed multiplier (mistv2 only). reduceLatency: Whether to reduce latency at potential quality cost (mistv2 only). pauseBetweenBrackets: Whether to add pauses between bracketed content (mistv2 only). phonemizeBetweenBrackets: Whether to phonemize bracketed content (mistv2 only). noTextNormalization: Whether to disable text normalization (mistv2 only). saveOovs: Whether to save out-of-vocabulary words (mistv2 only). inlineSpeedAlpha: Inline speed control markup. repetition_penalty: Token repetition penalty (arcana only, 1.0-2.0). temperature: Sampling temperature (arcana only, 0.0-1.0). top_p: Cumulative probability threshold (arcana only, 0.0-1.0). cCtSNrr1r1r1r2\zRimeTTSSettings.default_factoryNsegmentcCr5r6r7r1r1r1r2r8]r9 speedAlphacCr5r6r7r1r1r1r2r8^r9 reduceLatencycCr5r6r7r1r1r1r2r8_r9pauseBetweenBracketscCr5r6r7r1r1r1r2r8`r9phonemizeBetweenBracketscCr5r6r7r1r1r1r2r8ar9noTextNormalizationcCr5r6r7r1r1r1r2r8br9saveOovscCr5r6r7r1r1r1r2r8cr9inlineSpeedAlphacCr5r6r7r1r1r1r2r8dr9repetition_penaltycCr5r6r7r1r1r1r2r8er9 temperaturecCr5r6r7r1r1r1r2r8fr9top_pspeakervoice_aliases)__name__ __module__ __qualname____doc__rr<strr__annotations__r=floatr>boolr?r@rArBrCrDrErFrIrrr1r1r1r2r4Js  r4c@seZdZUdZedddZedBeBed<edddZ e dBeBed<ed ddZ e dBeBed <ed ddZ e dBeBed <d diZ eeeefed<dS)RimeNonJsonTTSSettingsa7Settings for RimeNonJsonTTSService. Parameters: segment: Text segmentation mode ("immediate", "bySentence", "never"). repetition_penalty: Token repetition penalty (1.0-2.0). temperature: Sampling temperature (0.0-1.0). top_p: Cumulative probability threshold (0.0-1.0). cCr5r6r7r1r1r1r2r8vr9zRimeNonJsonTTSSettings.r:Nr<cCr5r6r7r1r1r1r2r8wr9rDcCr5r6r7r1r1r1r2r8xr9rEcCr5r6r7r1r1r1r2r8yr9rFrGrHrI)rJrKrLrMrr<rNrrOrDrPrErFrIrrr1r1r1r2rRks   rRcseZdZUdZeZeed<GdddeZdddddddddd de d e e d e d e e d e e d e ede ede e de e de effddZdefddZdede dBfddZdee effddZde de fddZdede fd d!Zde d"e d#e de fd$d%Zde d&ede fd'd(Zd)edee efffd*d+ ZdYde d-e defd.d/Zdefd0d1Zdefd2d3Zd4e ffd5d6 Z!d4e"ffd7d8 Z#d4e$ffd9d: Z%fd;d<Z&fd=d>Z'd?d@Z(dAdBZ)dCdDZ*d-e fdEdFZ+d-e fdGdHZ,d-e fdIdJZ-dKe.dLe.dMe.de.fdNdOZ/dZd-e e fdPdQZ0dRdSZ1e2j3fd4e4dTe2ffdUdV Z5e6de d-e de7e4dffdWdXZ8Z9S)[RimeTTSServicezText-to-Speech service using Rime's websocket API. Uses Rime's websocket JSON API to convert text to speech with word-level timing information. Supports interruptions and maintains context across multiple messages within a turn. _settingsc@seZdZUdZejZeeed<dZ ee ed<dZ ee ed<dZ ee ed<dZee ed<dZee ed<dZeeed <dZeeed <dZeeed <dZeeed <dZeeed <dS)zRimeTTSService.InputParamsaConfiguration parameters for Rime TTS service. .. deprecated:: 0.0.105 Use ``settings=RimeTTSService.Settings(...)`` instead. Parameters: language: Language for synthesis. Defaults to English. segment: Text segmentation mode ("immediate", "bySentence", "never"). speed_alpha: Speech speed multiplier. repetition_penalty: Token repetition penalty (arcana only). temperature: Sampling temperature (arcana only). top_p: Cumulative probability threshold (arcana only). reduce_latency: Whether to reduce latency at potential quality cost (mistv2 only). pause_between_brackets: Whether to add pauses between bracketed content (mistv2 only). phonemize_between_brackets: Whether to phonemize bracketed content (mistv2 only). no_text_normalization: Whether to disable text normalization (mistv2 only). save_oovs: Whether to save out-of-vocabulary words (mistv2 only). r#Nr< speed_alpharDrErFreduce_latencypause_between_bracketsphonemize_between_bracketsno_text_normalization save_oovs)rJrKrLrMrr-r#rrOr<rNrUrPrDrErFrVrQrWrXrYrZr1r1r1r2 InputParamss r[Nzwss://users-ws.rime.ai/ws3) voice_idurlmodel sample_rateparamssettingstext_aggregatortext_aggregation_modeaggregate_sentencesapi_keyr\r]r^r_r`rarbrcrdc  sB|jddddddddddddddd} |dur |dd|| _|dur-|dd|| _|durd|d|sd|j| _|j| _|j| _|j| _|j | _ |j | _ |j | _ |j | _|j| _|j| _|j| _|durm| |tjd| | dd d d || d | d |_d |_|std g|jd|_||_||_d|_d |_ i|_!dS)aInitialize Rime TTS service. Args: api_key: Rime API key for authentication. voice_id: ID of the voice to use. .. deprecated:: 0.0.105 Use ``settings=RimeTTSService.Settings(voice=...)`` instead. url: Rime websocket API endpoint. model: Model ID to use for synthesis. .. deprecated:: 0.0.105 Use ``settings=RimeTTSService.Settings(model=...)`` instead. sample_rate: Audio sample rate in Hz. params: Additional configuration parameters. .. deprecated:: 0.0.105 Use ``settings=RimeTTSService.Settings(...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. text_aggregator: Custom text aggregator for processing input text. .. deprecated:: 0.0.95 Use an LLMTextProcessor before the TTSService for custom text aggregation. text_aggregation_mode: How to aggregate incoming text before synthesis. aggregate_sentences: Deprecated. Use text_aggregation_mode instead. .. deprecated:: 0.0.104 Use ``text_aggregation_mode`` instead. **kwargs: Additional arguments passed to parent class. arcanaN)r^rHr#r<rCr=rDrErFr>r?r@rArBr\rHr^r`FT)rcrdpush_text_framespush_stop_framespause_frame_processingappend_trailing_spacer_rapcmr)spell())aggregation_typer1)"Settings"_warn_init_param_moved_to_settingsrHr^r#r<rUr=rDrErFrVr>rWr?rXr@rYrArZrB apply_updatesuper__init__ _audio_format_sampling_rater_text_aggregation_mode_text_aggregator_api_key_url _receive_task_cumulative_time_extra_msg_fields) selfrer\r]r^r_r`rarbrcrdkwargsdefault_settings __class__r1r2rssz4       zRimeTTSService.__init__r$cCdS)zCheck if this service can generate processing metrics. Returns: True, as Rime service supports metrics generation. Tr1r}r1r1r2can_generate_metrics3z#RimeTTSService.can_generate_metricsr#cCt|SzConvert pipecat language to Rime language code. Args: language: The language to convert. Returns: The Rime-specific language code, or None if not supported. r3r}r#r1r1r2language_to_service_language; z+RimeTTSService.language_to_service_languagecCsN|jj|jj|j|jd}|jjdur|jj|d<|jjdur%|jj|d<|jjdur1|jj|d<|jjdkr]|jjdurC|jj|d<|jj durO|jj |d<|jj dur[|jj |d <|S|jj duri|jj |d <|jj durxt |jj |d <|jjdurt |jj|d <|jjdurt |jj|d <|jjdurt |jj|d<|S)a-Build query params for the WebSocket URL from current settings. Returns: Dictionary of query parameters for the WebSocket URL. Only explicitly-set values are included. Boolean mistv2 params are serialized with ``json.dumps()`` for the wire format. rGmodelId audioFormat samplingRateNlangr<r=rfrDrErFr>r?r@rArB)rTrHr^rtrur#r<r=rDrErFr>r?jsondumpsr@rArB)r}r`r1r1r2_build_ws_paramsFs@                   zRimeTTSService._build_ws_paramstextcCs d|dS)z!Wrap text in Rime spell function.rlrmr1)rr1r1r2SPELLss zRimeTTSService.SPELLsecondscCsd|ddS)z)Convenience method to create a pause tag.r1)rr1r1r2 PAUSE_TAGwszRimeTTSService.PAUSE_TAGwordphonemecCsd|jd<|||S)zConvenience method to support Rime's custom pronunciations feature. https://docs.rime.ai/api-reference/custom-pronunciation Tr@)r|replace)r}rrrr1r1r2 PRONOUNCE{s zRimeTTSService.PRONOUNCEspeedcCsF|jsi|_|jddd}d|t|g|jd<d|dS)z,Convenience method to support inline speeds.rC,[])r|getsplitjoinrN)r}rr speed_valsr1r1r2 INLINE_SPEEDs  zRimeTTSService.INLINE_SPEEDdeltacs>t|IdH}|r|jr|IdH|IdH|S)Apply a settings delta and reconnect if necessary. Since all settings are WebSocket URL query parameters, any setting change requires reconnecting to apply the new values. N)rr_update_settings _websocket _disconnect_connectr}rchangedrr1r2rs  zRimeTTSService._update_settingsr context_idcCs$||d}|jr||jO}i|_|S)z Build JSON message for Rime API.)r contextId)r|)r}rrmsgr1r1r2 _build_msgs  zRimeTTSService._build_msgcCddiS)zBuild clear operation message. operationclearr1rr1r1r2_build_clear_msgzRimeTTSService._build_clear_msgcCr)z&Build end-of-stream operation message.reosr1rr1r1r2_build_eos_msgrzRimeTTSService._build_eos_msgframec.t|IdH|j|_|IdHdS)zStart the service and establish websocket connection. Args: frame: The start frame containing initialization parameters. Nrrstartr_rurr}rrr1r2rzRimeTTSService.startc&t|IdH|IdHdS)z`Stop the service and close connection. Args: frame: The end frame. Nrrstoprrrr1r2rzRimeTTSService.stopcr)zcCancel current operation and clean up. Args: frame: The cancel frame. Nrrcancelrrrr1r2rrzRimeTTSService.cancelcLtIdH|IdH|jr"|js$|||j|_dSdSdS)z6Establish websocket connection and start receive task.Nrrr_connect_websocketrrz create_task_receive_task_handler _report_errorrrr1r2rs  zRimeTTSService._connectcBtIdH|jr||jIdHd|_|IdHdS)z.Close websocket connection and clean up tasks.Nrrrrz cancel_task_disconnect_websocketrrr1r2rs zRimeTTSService._disconnectc szB|jr|jjtjurWdS|}ddd|D}|jd|}dd|ji}t ||dIdH|_| d IdHWdSt yp}z!|j d ||d IdHd|_| d |IdHWYd}~dSd}~ww) z7Connect to Rime websocket API with configured settings.N&cs*|]\}}|dur|d|VqdSN=r1.0kvr1r1r2 (z4RimeTTSService._connect_websocket..? AuthorizationBearer )additional_headers on_connectedzError connecting:  error_msg exceptionon_connection_error) rstater"OPENrritemsryrxwebsocket_connect_call_event_handler Exception push_error)r} ws_paramsr`r]headerser1r1r2rs "z!RimeTTSService._connect_websocketc szlz"|IdH|jr#|jt|IdH|jIdHWntyC}z|jd||dIdHWYd}~nd}~wwW| IdHd|_| dIdHdSW| IdHd|_| dIdHdS| IdHd|_| dIdHw)z+Close websocket connection and reset state.NzError disconnecting: ron_disconnected) stop_all_metricsrsendrrrcloserrremove_active_audio_contextrr}rr1r1r2rs,&z$RimeTTSService._disconnect_websocketcC|jr|jStd)z3Get active websocket connection or raise exception.Websocket not connectedrrrr1r1r2_get_websocketzRimeTTSService._get_websocketcs:|IdH|r|t|IdHdSdS)z-Clear the Rime speech queue and stop metrics.N)rrrrrrr}rr1r1r2_close_contexts "zRimeTTSService._close_contextc||IdHdS)zIClear the Rime speech queue and stop metrics when the bot is interrupted.Nrrr1r1r2on_audio_context_interruptedsz+RimeTTSService.on_audio_context_interruptedcr)aSClear server-side state and stop metrics after the Rime context finishes playing. Rime does not send a server-side completion signal (e.g. ``done`` / ``end_of_stream`` / ``audio_end``), so we explicitly send a ``clear`` message to clean up any residual server-side state once all audio has been delivered. Nrrr1r1r2on_audio_context_completedsz)RimeTTSService.on_audio_context_completedwordsstartsendsc Csg}tt|||D]4\}\}}}|sq ||j} t|ddk} | r7|r7|d\} } | || f|d<q ||| fq |S)a@Calculate word timing pairs with proper spacing and punctuation. Args: words: List of words from Rime. starts: List of start times for each word. ends: List of end times for each word. Returns: List of (word, timestamp) pairs with proper timing. z,.!?r) enumeratezipstripr{rQappend) r}rrr word_pairsir start_time_adjusted_startis_punctuation prev_word prev_timer1r1r2_calculate_word_timess   z$RimeTTSService._calculate_word_timescsN|p|}|r |jsdSt|d|tddiIdHdS)"Flush any pending audio synthesis.N: flushing audiorflush)get_active_audio_context_idrr tracerrrr)r}rflush_idr1r1r2 flush_audio.s   "zRimeTTSService.flush_audioc s`|2z3dHW}t|}|r||dsq|d}|ddkr=tt|d|jd|d}| ||IdHq|ddkr|d i}|d g}|d g}|d g}|r|r| |||} | r|j | |d IdH|d|j |_ t d|j q|ddkr|tIdH|IdH|jd|ddIdH|q6dS)z$Process incoming websocket messages.Nrtypechunkdataaudior_ num_channelsr timestampsword_timestampsrrendrrzUpdated cumulative time to: errorError: message)r)rrloadsaudio_context_availablerrbase64 b64decoder_append_to_audio_contextradd_word_timestampsr{r debug push_framerrrreset_active_audio_context) r}r$rrrrrrrrr1r1r2_receive_messages7sB         z RimeTTSService._receive_messages directioncsLt||IdHt|ttfr"t|tr$|dgIdHdSdSdS)zPush frame and handle end-of-turn conditions. Args: frame: The frame to push. direction: The direction to push the frame. N)Resetr)rrr, isinstancerrr*r}rr/rr1r2r,_s zRimeTTSService.push_framec CsZt|d|dz|jr|jjtjur|IdHz;||s<||IdH| IdHt |dVd|_ |j ||d}| t|IdH||IdHWn1ty}z%td|dVt|dV|IdH|IdHWYd}~WdSd}~wwdVWdSty}ztd|dVWYd}~dSd}~ww) aGenerate speech from text using Rime's 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. : Generating TTS [rNr!r)rrUnknown error occurred: r")r r+rrr"CLOSEDrr&create_audio_contextstart_ttfb_metricsrr{rrrrrstart_tts_usage_metricsrr rr)r}rrrrr1r1r2run_ttsks6      zRimeTTSService.run_tts)rrr6):rJrKrLrMr4rorOr r[rNrintrrrQrsrrrdictrrrrPrrrrrrrrrrr rr rrrrrrrrrlistrrr.r DOWNSTREAMrr,r rr: __classcell__r1r1rr2rS~s &      -     ( (rScseZdZUdZeZeed<GdddeZddddddde de e d e j d e e d e e d e ed e effddZdefddZdede dBfddZede de deedffddZZS)RimeHttpTTSServicezRime HTTP-based text-to-speech service. Provides text-to-speech synthesis using Rime's HTTP API for batch processing. Suitable for use cases where streaming is not required. rTc@steZdZUdZejZeeed<dZ ee ed<dZ ee ed<dZ ee ed<dZeeed <dZee ed <dS) zRimeHttpTTSService.InputParamsarConfiguration parameters for Rime HTTP TTS service. .. deprecated:: 0.0.105 Use ``settings=RimeHttpTTSService.Settings(...)`` instead. Parameters: language: Language for synthesis. Defaults to English. pause_between_brackets: Whether to add pauses between bracketed content. phonemize_between_brackets: Whether to phonemize bracketed content. inline_speed_alpha: Inline speed control markup. speed_alpha: Speech speed multiplier. Defaults to 1.0. reduce_latency: Whether to reduce latency at potential quality cost. r#FrWrXNinline_speed_alphag?rUrV)rJrKrLrMrr-r#rrOrWrQrXrArNrUrPrVr1r1r1r2r[s r[N)r\r^r_r`rarer\aiohttp_sessionr^r_r`rac  s|jddddddddddddddd} |dur |dd|| _|dur-|dd|| _|durU|d|sU|j| _|j| _|j| _|j | _ |j | _ |j rR|j nd| _|dur^| |tjd |d d | d |||_||_d |_d |_dS)aInitialize Rime HTTP TTS service. Args: api_key: Rime API key for authentication. voice_id: ID of the voice to use. .. deprecated:: 0.0.105 Use ``settings=RimeHttpTTSService.Settings(voice=...)`` instead. aiohttp_session: Shared aiohttp session for HTTP requests. model: Model ID to use for synthesis. .. deprecated:: 0.0.105 Use ``settings=RimeHttpTTSService.Settings(model=...)`` instead. sample_rate: Audio sample rate in Hz. params: Additional configuration parameters. .. deprecated:: 0.0.105 Use ``settings=RimeHttpTTSService.Settings(...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional arguments passed to parent TTSService. mistv2Nr')r^rHr#r<r=r>r?r@rArBrCrDrErFr\rHr^r`T)r_rhpush_start_frameraz!https://users.rime.ai/v1/rime-ttsrkr1)rorprHr^r#rUr=rVr>rWr?rXr@rArCrqrrrsrx_session _base_urlrt) r}rer\rBr^r_r`rar~rrr1r2rss\&     zRimeHttpTTSService.__init__r$cCr)zCheck if this service can generate processing metrics. Returns: True, as Rime HTTP service supports metrics generation. Tr1rr1r1r2rrz'RimeHttpTTSService.can_generate_metricsr#cCrrrrr1r1r2rrz/RimeHttpTTSService.language_to_service_languagerrc Cs t|d|ddd|jdd}|jj|jj|jj|jj|jjd}|jj dur4|jj |d <||d <|jj |d <|jj |d <|j |d <|d dkrVd|d<d}nd}zzu|j j|j||d4IdHZ}|jdkrd|j}t|dV WdIdHWW|IdHdS||IdH|j}|j|j|||d2z3dHW} |IdH| Vq6WdIdHn 1IdHswYWnty} ztd| dVWYd} ~ nd} ~ wwW|IdHdSW|IdHdS|IdHw)aGenerate speech from text using Rime's HTTP API. Args: text: The text to synthesize into speech. context_id: The context ID for tracking audio frames. Yields: Frame: Audio frames containing the synthesized speech. r3rz audio/pcmrzapplication/json)Acceptrz Content-Type)rr=r>r?r@NrCrrGrrrfz audio/wavrGTF)rrzRime TTS error: HTTP r5)strip_wav_headerrr4)r r+rxrTr#r=r>r?r@rCrHr^r_rEpostrFstatusr stop_ttfb_metricsr9 chunk_size"_stream_audio_frames_from_iteratorcontent iter_chunkedr) r}rrrpayloadneed_to_strip_wav_headerresponse error_message CHUNK_SIZErrr1r1r2r:"sj            ("zRimeHttpTTSService.run_tts)rJrKrLrMr4rorOr r[rNraiohttp ClientSessionr;rsrQrrrr rrr:r?r1r1rr2r@s:  _ (r@cseZdZUdZeZeed<GdddeZdddddddddd d e d e e d e d e e d e de e de ede ede e de e ffddZde fddZdede fddZdeffdd Zdeffdd Zdeffd d! Zejfded"effd#d$ Zfd%d&Zfd'd(Zd)d*Zd+d,Zd-d.Z d:d/e e fd0d1Z!d2d3Z"e#d4e d/e de$edffd5d6Z%d7e&de'e e(fffd8d9 Z)Z*S);RimeNonJsonTTSServiceaPipecat TTS service for Rime's non-JSON WebSocket API. .. deprecated:: 0.0.102 Arcana now supports JSON WebSocket with word-level timestamps via the ``wss://users-ws.rime.ai/ws3`` endpoint. Use :class:`RimeTTSService` with ``model="arcana"`` instead. This service enables Text-to-Speech synthesis over WebSocket endpoints that require plain text (not JSON) messages and return raw audio bytes. Limitations: - Does not support word-level timestamps or context IDs. - Intended specifically for integrations where the TTS provider only accepts and returns non-JSON messages. rTc@szeZdZUdZdZeeed<dZee ed<dZ ee ed<dZ ee ed<dZ ee ed<dZeee efed<dS) z!RimeNonJsonTTSService.InputParamsamConfiguration parameters for Rime Non-JSON WebSocket TTS service. .. deprecated:: 0.0.105 Use ``settings=RimeNonJsonTTSService.Settings(...)`` instead. Args: language: Language for synthesis. Defaults to English. segment: Text segmentation mode ("immediate", "bySentence", "never"). repetition_penalty: Token repetition penalty (1.0-2.0). temperature: Sampling temperature (0.0-1.0). top_p: Cumulative probability threshold (0.0-1.0). extra: Additional parameters to pass to the API (for future compatibility). Nr#r<rDrErFextra)rJrKrLrMr#rrrOr<rNrDrPrErFrYr<rr1r1r1r2r[ys r[Nzwss://users.rime.ai/wsrk) r\r]r^ audio_formatr_r`rardrcrer\r]r^rZr_r`rardrcc s|jdddddddd} |dur|dd|| _|dur&|dd|| _|durE|d|sE|j| _|j| _|j| _|j| _|j| _|durN| |t j d || | dddd| d | ||_ ||_ ||_||_|ry|jry|jj|jd|_dS) aInitialize Rime Non-JSON WebSocket TTS service. Args: api_key: Rime API key for authentication. voice_id: ID of the voice to use. .. deprecated:: 0.0.105 Use ``settings=RimeNonJsonTTSService.Settings(voice=...)`` instead. url: Rime websocket API endpoint. model: Model ID to use for synthesis. .. deprecated:: 0.0.105 Use ``settings=RimeNonJsonTTSService.Settings(model=...)`` instead. audio_format: Audio format to use. sample_rate: Audio sample rate in Hz. params: Additional configuration parameters. .. deprecated:: 0.0.105 Use ``settings=RimeNonJsonTTSService.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. Set to ``TextAggregationMode.SENTENCE`` to aggregate text into sentences before synthesis, or ``TextAggregationMode.TOKEN`` to stream tokens directly for lower latency. text_aggregation_mode: How to aggregate text before synthesis. **kwargs: Additional arguments passed to parent class. Nrf)rHr^r#r<rDrErFr\rHr^r`T)r_rdrcrhrDrirjrar1)rorprHr^r#r<rDrErFrqrrrsrtrurxryrYrTupdaterz) r}rer\r]r^rZr_r`rardrcr~rrr1r2rssX2        zRimeNonJsonTTSService.__init__r$cCr)zCheck if this service can generate processing metrics. Returns: True, as Rime Non-JSON WebSocket service supports metrics generation. Tr1rr1r1r2rrz*RimeNonJsonTTSService.can_generate_metricsr#cCr)a>Convert pipecat Language enum to Rime language code. Args: language: The Language enum value to convert. Returns: Three-letter Rime language code (e.g., 'eng' for English). Falls back to the language's base code with a warning if not in the verified list. rrr1r1r2rs z2RimeNonJsonTTSService.language_to_service_languagercr)zStart the Rime Non-JSON WebSocket TTS service. Args: frame: The start frame containing initialization parameters. Nrrrr1r2r rzRimeNonJsonTTSService.startcr)z&Stop the service and close connection.Nrrrr1r2rzRimeNonJsonTTSService.stopcr)z&Cancel current operation and clean up.Nrrrr1r2rr\zRimeNonJsonTTSService.cancelr/cst||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)rrr,r2rr1r2r,!sz RimeNonJsonTTSService.push_framecr)z6Establish WebSocket connection and start receive task.Nrrrr1r2r*s  zRimeNonJsonTTSService._connectcr)z.Close WebSocket connection and clean up tasks.Nrrrr1r2r2s z!RimeNonJsonTTSService._disconnectc s|z|jr|jjtjurWdS|jj|jj|j|jd}|jj dur(|jj |d<|jj dur4|jj |d<|jj dur@|jj |d<|jj durL|jj |d<|jj durX|jj |d<||jjdd d |D}|jd |}d d |ji}t||ddIdH|_|dIdHWdSty}z!|jd||dIdHd|_|d|IdHWYd}~dSd}~ww)z:Establish WebSocket connection to Rime non-JSON websocket.Nrrr<rDrErFrcsrrr1rr1r1r2rSrz;RimeNonJsonTTSService._connect_websocket..rrri)rmax_sizerr4rr)rrr"rrTrHr^rtrur#r<rDrErFr[rYrrryrxrrrr)r} settings_dictr`r]rrr1r1r2r;sB          "z(RimeNonJsonTTSService._connect_websocketc sz^z"|IdH|jr#|jdIdH|jIdHtdWntyC}z|jd||dIdHWYd}~nd}~wwWd|_|dIdHdSWd|_|dIdHdSd|_|dIdHw)z.Close WebSocket connection and clean up state.Nzz)Disconnected from Rime non-JSON websocketr4rr) rrrrr r+rrrrr1r1r2r_s( &z+RimeNonJsonTTSService._disconnect_websocketcCr)z3Get active WebSocket connection or raise exception.rrrr1r1r2rnrz$RimeNonJsonTTSService._get_websocketrcs2|jsdSt|d|jdIdHdS)rNrz)rr rrrr1r1r2rts z!RimeNonJsonTTSService.flush_audioc s|2zF3dHW}z!t|tr+|IdHt||jd|d}||IdHWqtyK}z|j d||dIdHWYd}~qd}~ww6dS)z6Process incoming WebSocket messages (raw audio bytes).Nrrr#r) rr1bytesrLrr_rr,rr)r}r$rrr1r1r2r.|s$ &z'RimeNonJsonTTSService._receive_messagesrc Cs t|d|dz]|jr|jjtjur|IdHz||IdH| |IdHWn1t yc}z%t d|dVt |dV| IdH|IdHWYd}~WdSd}~wwdVWdSt y}zt d|dVWYd}~dSd}~ww)aGenerate speech from text using Rime'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. r3rNr4r5r!)r r+rrr"r6rrrr9rr rr)r}rrrr1r1r2r:s*    zRimeNonJsonTTSService.run_ttsrcsBt|IdH}|rtd|IdH|IdH|S)rNzrr,rrrrrrr.r rr:rr<rrr?r1r1rr2rXesf     j    $ &rX)?rMr'r dataclassesrrtypingrrrrrrVlogurur pydanticr pipecat.frames.framesr r r rrrrrr"pipecat.processors.frame_processorrpipecat.services.settingsrrrpipecat.services.tts_servicerrrrpipecat.transcriptions.languagerr'pipecat.utils.text.base_text_aggregatorr'pipecat.utils.text.skip_tags_aggregatorr(pipecat.utils.tracing.service_decoratorsr websockets.asyncio.clientr!rwebsockets.protocolr"ModuleNotFoundErrorrr"rrNr3r4rRrSr@rXr1r1r1r2sL  ,       V