o iK@sdZddlZddlmZmZddlmZmZmZm Z m Z ddl Z ddl m Z ddlmZddlmZmZmZmZddlmZmZmZdd lmZdd lmZmZdd lmZd ed e e fddZ!eGdddeZ"GdddeZ#dS)zMiniMax text-to-speech service implementation. This module provides integration with MiniMax's T2A (Text-to-Audio) API for streaming text-to-speech synthesis. N) dataclassfield)AnyAsyncGeneratorMappingOptionalSelf)logger) BaseModel) ErrorFrameFrame StartFrameTTSAudioRawFrame) NOT_GIVEN TTSSettings _NotGiven) TTSService)Languageresolve_language) traced_ttslanguagereturnc CsNitjdtjdtjdtjdtjdtjdtjdtjdtj d tj d tj d tj d tj d tjdtjdtjdtjditjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtjdtj d tj!d!tj"d"tj#d#tj$d$tj%d%tj&d&tj'd'tj(d(i}t)||d)d*S)+zConvert a Language enum to MiniMax language format. Args: language: The Language enum value to convert. Returns: The corresponding MiniMax language name, or None if not supported. AfrikaansArabic BulgarianCatalanCzechDanishGermanGreekEnglishSpanishPersianFinnishFilipinoFrenchHebrewHindiCroatian Hungarian IndonesianItalianJapaneseKoreanMalay NorwegianNynorskDutchPolish PortugueseRomanianRussianSlovak SlovenianSwedishTamilThaiTurkish Ukrainian Vietnamesez Chinese,YueChineseF) use_base_code)*rAFARBGCACSDADEELENESFAFIFILFRHEHIHRHUIDITJAKOMSNBNNNLPLPTRORUSKSLSVTATHTRUKVIYUEZHr)r LANGUAGE_MAPriP/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/minimax/tts.pylanguage_to_minimax_language!s       !"#+rkcs eZdZUdZedddZedBeBed<edddZ edBeBed<ed ddZ e dBeBed <ed ddZ e dBeBed <ed ddZedBeBed<edddZedBeBed<edddZe dBeBed<edee efdeffdd ZZS)MiniMaxTTSSettingsaSettings for MiniMaxHttpTTSService. Parameters: speed: Speech speed (range: 0.5 to 2.0). volume: Speech volume (range: 0 to 10). pitch: Pitch adjustment (range: -12 to 12). emotion: Emotional tone (options: "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm", "fluent"). text_normalization: Enable text normalization (Chinese/English). latex_read: Enable LaTeX formula reading. language_boost: Language boost string for multilingual support. cCtSNrriririrjgzMiniMaxTTSSettings.)default_factoryNspeedcCrmrnroriririrjrphrqvolumecCrmrnroriririrjrpirqpitchcCrmrnroriririrjrpjrqemotioncCrmrnroriririrjrpkrqtext_normalizationcCrmrnroriririrjrplrq latex_readcCrmrnroriririrjrpmrqlanguage_boostsettingsrcst|}|dd}t|trE|d|d|d|d|d|d|d|d|d|d|d |d t|S) uConstruct settings from a plain dict, destructuring legacy nested dicts. Handles ``voice_setting`` (with ``vol`` → ``volume`` rename) and ``audio_setting`` (with prefixed field mapping). voice_settingNrsrtvolrurvrwrx)dictpop isinstance setdefaultgetsuper from_mapping)clsrzflatvoice __class__rirjros   zMiniMaxTTSSettings.from_mapping)__name__ __module__ __qualname____doc__rrsfloatr__annotations__rtruintrvstrrwboolrxry classmethodrrrr __classcell__ririrrjrlXs  (rlcseZdZUdZeZeed<GdddeZddddddddd e d e d e d e e d e e de j de e dede ede effddZdefddZdede e fddZdeffdd Zede de deedffd d!ZZS)"MiniMaxHttpTTSServiceaText-to-speech service using MiniMax's T2A (Text-to-Audio) API. Provides streaming text-to-speech synthesis using MiniMax's HTTP API with support for various voice settings, emotions, and audio configurations. Supports real-time audio streaming with configurable voice parameters. Platform documentation: https://www.minimax.io/platform/document/T2A%20V2?key=66719005a427f0c8a5701643 _settingsc@seZdZUdZejZeeed<dZ ee ed<dZ ee ed<dZ ee ed<dZeeed <dZeeed <dZeeed <dZeeed <dZeeed <dS)z!MiniMaxHttpTTSService.InputParamsaConfiguration parameters for MiniMax TTS. .. deprecated:: 0.0.105 Use ``MiniMaxHttpTTSService.Settings`` directly via the ``settings`` parameter instead. Parameters: language: Language for TTS generation. Supports 40 languages. Note: Filipino, Tamil, and Persian require speech-2.6-* models. speed: Speech speed (range: 0.5 to 2.0). volume: Speech volume (range: 0 to 10). pitch: Pitch adjustment (range: -12 to 12). emotion: Emotional tone (options: "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm", "fluent"). english_normalization: Deprecated; use `text_normalization` instead .. deprecated:: 0.0.96 The `english_normalization` parameter is deprecated and will be removed in a future version. Use the `text_normalization` parameter instead. text_normalization: Enable text normalization (Chinese/English). latex_read: Enable LaTeX formula reading. exclude_aggregated_audio: Whether to exclude aggregated audio in final chunk. r?rsrtrruNrvenglish_normalizationrwrxexclude_aggregated_audio)rrrrrrHrrrrsrrtrurrvrrrrwrxrriririrj InputParamss rz https://api.minimax.io/v1/t2a_v2NT)base_urlmodelvoice_id sample_ratestreamparamsrzapi_keyrgroup_idrraiohttp_sessionrrrrzc  s|jddddddddddd } |dur|dd|| _|dur)|dd || _| dur|d | s| j| _| j| _| j| _| j| _| jrR| | j} | rR| | _ | j rogd }| j |vrc| j | _ n t d | j d || jdurddl}||d|dtWdn1swY| j| _| jdur| j| _| dur| | tjd|dd| d| ||_||_||_|d||_||_d|_d|_d|_d|_ dS)aInitialize the MiniMax TTS service. Args: api_key: MiniMax API key for authentication. base_url: API base URL, defaults to MiniMax's T2A endpoint. Global: https://api.minimax.io/v1/t2a_v2 Mainland China: https://api.minimaxi.chat/v1/t2a_v2 Western United States: https://api-uw.minimax.io/v1/t2a_v2 group_id: MiniMax Group ID to identify project. model: TTS model name. Defaults to "speech-02-turbo". Options include: "speech-2.6-hd", "speech-2.6-turbo" (latest, supports Filipino/Tamil/Persian), "speech-02-hd", "speech-02-turbo", "speech-01-hd", "speech-01-turbo". .. deprecated:: 0.0.105 Use ``settings=MiniMaxHttpTTSService.Settings(model=...)`` instead. voice_id: Voice identifier. Defaults to "Calm_Woman". .. deprecated:: 0.0.105 Use ``settings=MiniMaxHttpTTSService.Settings(voice=...)`` instead. aiohttp_session: aiohttp.ClientSession for API communication. sample_rate: Output audio sample rate in Hz. If None, uses pipeline default. stream: Whether to use streaming mode. Defaults to True. params: Additional configuration parameters. .. deprecated:: 0.0.105 Use ``settings=MiniMaxHttpTTSService.Settings(...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional arguments passed to parent TTSService. zspeech-02-turbo Calm_WomanNrr) rrrrsrtruryrvrwrxrrrr)happysadangryfearful disgusted surprisedneutralfluentzUnsupported emotion: z. Supported emotions: alwayszzParameter `english_normalization` is deprecated and will be removed in a future version. Use `text_normalization` instead.T)rpush_start_framepush_stop_framesrzz ?GroupId=ipcmri)!Settings"_warn_init_param_moved_to_settingsrrrsrtrurxrlanguage_to_service_languageryrvr warningrwarningscatch_warnings simplefilterwarnDeprecationWarningrw apply_updater__init___api_key _group_id_stream _base_url_session_audio_bitrate _audio_format_audio_channel_audio_sample_rate)selfrrrrrrrrrrzkwargsdefault_settings service_langsupported_emotionsrrrirjrs2           zMiniMaxHttpTTSService.__init__rcCsdS)zCheck if this service can generate processing metrics. Returns: True, as MiniMax service supports metrics generation. Tri)rririrjcan_generate_metricsDsz*MiniMaxHttpTTSService.can_generate_metricsrcCst|S)zConvert a Language enum to MiniMax service language format. Args: language: The language to convert. Returns: The MiniMax-specific language name, or None if not supported. )rk)rrririrjrLs z2MiniMaxHttpTTSService.language_to_service_languageframecs2t|IdH|j|_td|jdS)zStart the MiniMax TTS service. Args: frame: The start frame containing initialization parameters. Nz*MiniMax TTS initialized with sample_rate: )rstartrrr debug)rrrrirjrWszMiniMaxHttpTTSService.starttext context_idc Cst|d|dddd|jd}|jj|jj|jj|jjd}|jjdur1|jj|d <|jj dur=|jj |d <|jj durI|jj |d <|j |j |j |jd }|j|||jj|d }|jjdurk|jj|d<z}zJ|jj|j||d4IdH-}|jdkrd|j}t|dV WdIdHWW|IdHdS||IdHt} |j} |j| 2z3dHW} | sq| | d| vr| d} | d| d} | dkr| dkr| | d} n| | | }| | d} zt |dd!d}d|vr tdWq|"di}|sWq|"d}|s"Wqt#dt$|| dD]I}|||| d}|s=q,zt%&|}|rW|IdHt'||j(d|dVWq,t)yu}zt*d|WYd}~q,d}~wwWn#tj+y}zt*d |d!|dd"WYd}~qd}~wwd| vsq6WdIdHn 1IdHswYWnt,y}ztd#||d$VWYd}~nd}~wwW|IdHdSW|IdHdS|IdHw)%aGenerate TTS audio from text using MiniMax'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. z: Generating TTS []z!application/json, text/plain, */*zapplication/jsonzBearer )acceptz Content-Type Authorization)rrsr|ruNrvrwrx)bitrateformatchannelr)rr{ audio_settingrrry)headersjsonzMiniMax TTS error: HTTP )errorsdata:rzutf-8 extra_infoz$Received final chunk with extra infodataaudior)rr num_channelsrz Error converting hex to binary: zError decoding JSON: z, data: dzUnknown error occurred: )r exception)-r rrrrrsrtrurvrwrxrrrrrrryrpostrstatusr stop_ttfb_metricsstart_tts_usage_metrics bytearray chunk_sizecontent iter_chunkedextendfindrloadsdecoderrangelenbytesfromhexrr ValueErrorrJSONDecodeError Exception)rrrrr{rpayloadresponse error_messagebuffer CHUNK_SIZEchunkr next_start data_blockr chunk_data audio_datai hex_chunk audio_chunkeririrjrun_ttsas              T            *Q "zMiniMaxHttpTTSService.run_tts)rrrrrlrrr rrraiohttp ClientSessionrrrrrrr rrrr rrririrrjrsN  '      (r)$rr dataclassesrrtypingrrrrrrlogurur pydanticr pipecat.frames.framesr r r rpipecat.services.settingsrrrpipecat.services.tts_servicerpipecat.transcriptions.languagerr(pipecat.utils.tracing.service_decoratorsrrrkrlrriririrjs     7+