o i84@s*UdZddlmZmZddlmZmZmZmZddl m Z ddl m Z ddl mZddlmZmZddlmZmZmZmZdd lmZmZmZdd lmZdd lmZmZdd l m!Z!d dd dZ"ee#e$fe%d<dedee#fddZ&de'de(e'e'ffddZ)eGdddeZ*GdddeZ+dS)aCamb.ai MARS text-to-speech service implementation. This module provides TTS functionality using Camb.ai's MARS model family, offering high-quality text-to-speech synthesis with streaming support. Features: - MARS models: mars-flash (fast), mars-pro (high quality) - 140+ languages supported - Real-time streaming via official SDK - Model-specific sample rates: mars-pro (48kHz), mars-flash (22.05kHz) ) dataclassfield)AnyAsyncGeneratorDictOptional)StreamTtsOutputConfiguration) AsyncCambAI)logger) BaseModelField) ErrorFrameFrame StartFrameTTSAudioRawFrame) NOT_GIVEN TTSSettings _NotGiven) TTSService)Languageresolve_language) traced_tts"Vi) mars-flashzmars-pro mars-instructMODEL_SAMPLE_RATESlanguagereturncCsitjdtjdtjdtjdtjdtjdtjdtjdtj dtj dtj dtj dtj d tjd tjd tjd tjd itjd tjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtj dtj!dtj"ditj#dtj$dtj%dtj&d tj'd!tj(d"tj)d#tj*d$tj+d%tj,d&tj-d'tj.d(tj/d)tj0d*tj1d+tj2d,tj3d-tj4d.tj5d/tj6d0tj7d1tj8d2tj9d3tj:d4tj;d5tjd8i }t?||d9d:S);zConvert a Pipecat Language enum to Camb.ai language code. Args: language: The Language enum value to convert. Returns: The corresponding Camb.ai language code (BCP-47 format), or None if not supported. en-uszen-gbzen-auzes-eszes-mxzfr-frzfr-cazde-dezit-itzpt-ptzpt-brznl-nlzpl-plzru-ruzja-jpzko-krzzh-cnzzh-twzar-sazhi-inztr-trzvi-vnzth-thzid-idzms-myzsv-sezda-dkzno-nozfi-fizcs-czzel-grzhe-ilzhu-huzro-rozsk-skzuk-uazbg-bgzhr-hrzsr-rszsl-sizca-eszeu-eszgl-eszaf-zazsw-kezta-inzte-inzbn-inzmr-inzgu-inzkn-inzml-inzpa-inzur-pkzfa-irztl-phT) use_base_code)@rENEN_USEN_GBEN_AUESES_ESES_MXFRFR_FRFR_CADEDE_DEITPTPT_BRPT_PTNLPLRUJAKOZHZH_CNZH_TWARHITRVITHIDMSSVDANOFICSELHEHUROSKUKBGHRSRSLCAEUGLAFSWTATEBNMRGUKNMLPAURFATLr)r LANGUAGE_MAPr_M/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/camb/tts.pylanguage_to_camb_language.s       !"#$%&'()*+,-./01234ArabuffercCs(t|dd}|d|||dfS)zSplit buffer into aligned audio (2-byte samples) and remainder. Args: buffer: Raw audio bytes to align. Returns: Tuple of (aligned audio bytes, remaining bytes). N)len)rb aligned_sizer_r_r`_get_aligned_audio{s rfc@sJeZdZUdZedddZeeBed<edddZ e dBeBed<dS) CambTTSSettingsa5Settings for CambTTSService. Parameters: voice: Camb.ai voice ID. Overrides ``TTSSettings.voice`` (str) because Camb.ai uses integer voice IDs. user_instructions: Custom instructions for mars-instruct model only. Ignored for other models. Max 1000 characters. cCtSNrr_r_r_r`zCambTTSSettings.)default_factoryvoicecCrhrirjr_r_r_r`rkrlNuser_instructions) __name__ __module__ __qualname____doc__rrnintr__annotations__rostrr_r_r_r`rgs  "rgcseZdZUdZeZeed<GdddeZdddddddde d e e d e e d e d e e d e ede effddZ defddZdede e fddZdeffdd Zede de deedffddZZS)CambTTSServiceaCamb.ai MARS text-to-speech service using the official SDK. Converts text to speech using Camb.ai's MARS TTS models with support for multiple languages. Models: - mars-flash: Fast inference, 22.05kHz output (default) - mars-pro: High quality, 48kHz output Example:: # Basic usage with mars-flash (fast) tts = CambTTSService( api_key="your-api-key", settings=CambTTSService.Settings( model="mars-flash" ) ) # High quality with mars-pro tts = CambTTSService( api_key="your-api-key", settings=CambTTSService.Settings( voice=12345, model="mars-pro", ) ) _settingsc@s>eZdZUdZejZeeed<e ddddZ ee ed<dS)zCambTTSService.InputParamsaInput parameters for Camb.ai TTS configuration. .. deprecated:: 0.0.105 Use ``settings=CambTTSService.Settings(...)`` instead. Parameters: language: Language for synthesis (BCP-47 format). Defaults to English. user_instructions: Custom instructions for mars-instruct model only. Ignored for other models. Max 1000 characters. rNiztCustom instructions for mars-instruct model only. Use to control tone, style, or pronunciation. Max 1000 characters.)default max_length descriptionro) rprqrrrsrr rrrur rorvr_r_r_r` InputParamss  r|NgN@)voice_idmodeltimeout sample_rateparamssettingsapi_keyr}r~rrrrc s|jddddd} |dur|dd|| _|dur#|dd|| _|dur@|d |s@|jdur7|j| _|jdur@|j| _|durI| || j} |rg|t| krgt d | d t| d |d t j d|dd| d|||_ ||_d|_dS)aWInitialize the Camb.ai TTS service. Args: api_key: Camb.ai API key for authentication. voice_id: Voice ID to use. .. deprecated:: 0.0.105 Use ``settings=CambTTSService.Settings(voice=...)`` instead. model: TTS model to use. Options: "mars-flash" (fast), "mars-pro" (high quality). .. deprecated:: 0.0.105 Use ``settings=CambTTSService.Settings(model=...)`` instead. timeout: Request timeout in seconds. Defaults to 60.0 (minimum recommended by Camb.ai). sample_rate: Audio sample rate in Hz. If None, uses model-specific default. params: Additional voice parameters. If None, uses defaults. .. deprecated:: 0.0.105 Use ``settings=CambTTSService.Settings(...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional arguments passed to parent TTSService. rix?rN)r~rnrror~r}rnrz Camb.ai's z model only supports z Hz sample rate. Current rate of zHz may cause issues.T)rpush_start_framepush_stop_framesrr_)Settings"_warn_init_param_moved_to_settingsr~rnrro apply_updatergetr warningsuper__init___api_key_timeout_client) selfrr}r~rrrrkwargsdefault_settings_model __class__r_r`rsN'       zCambTTSService.__init__rcCsdS)zCheck if this service can generate processing metrics. Returns: True, as Camb.ai service supports metrics generation. Tr_)rr_r_r`can_generate_metrics$sz#CambTTSService.can_generate_metricsrcCst|S)zConvert a Language enum to Camb.ai language format. Args: language: The language to convert. Returns: The Camb.ai-specific language code, or None if not supported. )ra)rrr_r_r`language_to_service_language,s z+CambTTSService.language_to_service_languageframecsFt|IdHt|j|jd|_|js!t|j j d|_ dSdS)zStart the Camb.ai TTS service. Args: frame: The start frame containing initialization parameters. N)rrr) rstartr rrr_init_sample_raterrrxr~ _sample_rate)rrrr_r`r7s zCambTTSService.starttext context_idc Cst|d|dt|dkrtd|dd}z||jj|jj|jjtddd}|jjd kr?|jj r?|jj |d <| |IdH|j dusPJd d }|j j j di|2z%3dHW}|r|IdH||7}t|\}}|rt||jd |dVq\6t|dkrt|\}}|rt||jd |dVWdSWdSWdSty}ztd|dVWYd}~dSd}~ww)a,Generate speech from text using Camb.ai's TTS API. Args: text: The text to synthesize into speech (max 3000 characters). context_id: The context ID for tracking audio frames. Yields: Frame: Audio frames containing the synthesized speech. z: Generating TTS []i z:Text too long for Camb.ai TTS (max 3000 chars), truncatingN pcm_s16le)format)rr}r speech_modeloutput_configurationrroz#Camb.ai TTS service not initialized)audior num_channelsrrczCamb.ai TTS error: )errorr_)r debugrdrrxrnrr~rrostart_tts_usage_metricsrtext_to_speechttsstop_ttfb_metricsrfrr Exceptionr ) rrr tts_kwargs audio_bufferchunk aligned_audio_er_r_r`run_ttsEs\         zCambTTSService.run_tts)rprqrrrsrgrrur r|rvrrtfloatrboolrrrrrrrrr __classcell__r_r_rr`rws>  X (rwN),rs dataclassesrrtypingrrrrcambr camb.clientr logurur pydanticr r pipecat.frames.framesr rrrpipecat.services.settingsrrrpipecat.services.tts_servicerpipecat.transcriptions.languagerr(pipecat.utils.tracing.service_decoratorsrrrvrtrurabytestuplerfrgrwr_r_r_r`s*      M