o il8 @srdZddlZddlZddlZddlmZmZddlmZm Z m Z ddl Z ddl m Z ddlmZddlmZddlmZmZmZmZmZmZmZdd lmZdd lmZmZm Z dd l!m"Z"dd l#m$Z$zdd l%m&Z&ddl'm(Z(m)Z)m*Z*ddl+m,Z,Wn e-yZ.ze /de.e /de0de.dZ.[.wwdZ1dedZ2eGdddeZ3Gddde"Z4dS)z+Hume Text-to-Speech service implementation.N) dataclassfield)AnyAsyncGeneratorOptional)logger) BaseModel)version) CancelFrameEndFrameFrameInterruptionFrame StartFrameTTSAudioRawFrameTTSStoppedFrame)FrameDirection) NOT_GIVEN TTSSettings _NotGiven) TTSService) traced_tts)AsyncHumeClient) FormatPcmPostedUtterancePostedUtteranceVoiceWithId)TimestampMessagez Exception: zAIn order to use Hume, you need to `pip install pipecat-ai[hume]`.zMissing module: ipipecat)zX-Hume-Client-NamezX-Hume-Client-Versionc@sleZdZUdZedddZedBeBed<edddZ e dBeBed<ed ddZ e dBeBed <dS) HumeTTSSettingszSettings for HumeTTSService. Parameters: description: Natural-language acting directions (up to 100 characters). speed: Speaking-rate multiplier (0.5-2.0). trailing_silence: Seconds of silence to append at the end (0-5). cCtSNrr!r!M/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/hume/tts.py=zHumeTTSSettings.)default_factoryN descriptioncCrrr r!r!r!r"r#>r$speedcCrrr r!r!r!r"r#?r$trailing_silence) __name__ __module__ __qualname____doc__rr&strr__annotations__r'floatr(r!r!r!r"r3s "rc s&eZdZUdZeZeed<GdddeZddde ddde e de e d e ed e e d e ed df fd dZ d efddZded dffdd ZddZded dffdd Zded dffdd Zejfdedeffdd Zde ded dfdd Zed!e d"e d eedffd#d$ZZ S)%HumeTTSServiceaHume Octave Text-to-Speech service. Streams PCM audio via Hume's HTTP output streaming (JSON chunks) endpoint using the Python SDK and emits ``TTSAudioRawFrame`` frames suitable for Pipecat transports. Supported features: - Generates speech from text using Hume TTS. - Streams PCM audio. - Supports word-level timestamps for precise audio-text synchronization. - Supports dynamic updates of voice and synthesis parameters at runtime. - Provides metrics for Time To First Byte (TTFB) and TTS usage. _settingsc@sBeZdZUdZdZeeed<dZee ed<dZ ee ed<dS)zHumeTTSService.InputParamsaOptional synthesis parameters for Hume TTS. .. deprecated:: 0.0.105 Use ``settings=HumeTTSService.Settings(...)`` instead. Parameters: description: Natural-language acting directions (up to 100 characters). speed: Speaking-rate multiplier (0.5-2.0). trailing_silence: Seconds of silence to append at the end (0-5). Nr&r'r() r)r*r+r,r&rr-r.r'r/r(r!r!r!r" InputParamsTs  r2N)api_keyvoice_idparams sample_ratesettingsr3r4r5r6r7returnc s|ptd}|s td|tkrtdtd||jddddddd}|dur4|dd||_|durK|d |sK|j |_ |j |_ |j |_ |durT| |t jd|d d d |d |tjtd |_t||jd|_d|_d|_dS)aInitialize the HumeTTSService. Args: api_key: Hume API key. If omitted, reads the ``HUME_API_KEY`` environment variable. voice_id: ID of the voice to use. Only voice IDs are supported; voice names are not. .. deprecated:: 0.0.105 Use ``settings=HumeTTSService.Settings(voice=...)`` instead. params: Optional synthesis controls (acting instructions, speed, trailing silence). .. deprecated:: 0.0.105 Use ``settings=HumeTTSService.Settings(...)`` instead. sample_rate: Output sample rate for emitted PCM frames. Defaults to 48_000 (Hume). settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional arguments passed to the parent class. HUME_API_KEYzAHumeTTSService requires an API key (env HUME_API_KEY or api_key=)zHume TTS streams at z Hz; configured sample_rate=N)modelvoicelanguager&r'r(r4r;r5FT)r6push_text_framespush_stop_framespush_start_framer7)headers)r3 httpx_clientr!)osgetenv ValueErrorHUME_SAMPLE_RATErwarningSettings"_warn_init_param_moved_to_settingsr;r&r'r( apply_updatesuper__init__httpx AsyncClientDEFAULT_HEADERS _http_clientr_client _audio_bytes_cumulative_time)selfr3r4r5r6r7kwargsdefault_settings __class__r!r"rMdsN     zHumeTTSService.__init__cCsdS)zoCan generate metrics. Returns: True if metrics can be generated, False otherwise. Tr!rUr!r!r"can_generate_metricssz#HumeTTSService.can_generate_metricsframecs t|IdH|dS)zNStart the service. Args: frame: The start frame. N)rLstart _reset_staterUr\rXr!r"r]s zHumeTTSService.startcCs d|_dS)zReset internal state variables.rCN)rTrZr!r!r"r^s zHumeTTSService._reset_statec@t|IdHt|dr|jr|jIdHdSdSdS)zaStop the service and cleanup resources. Args: frame: The end frame. NrQ)rLstophasattrrQacloser_rXr!r"ra zHumeTTSService.stopcr`)zfCancel the service and cleanup resources. Args: frame: The cancel frame. NrQ)rLcancelrbrQrcr_rXr!r"rerdzHumeTTSService.cancel directioncsTt||IdHt|ttfr&|t|tr(|dgIdHdSdSdS)zPush a frame and handle state changes. Args: frame: The frame to push. direction: The direction to push the frame. N)Resetr)rL push_frame isinstancer rr^add_word_timestamps)rUr\rfrXr!r"rhs zHumeTTSService.push_framekeyvaluecsttdtjdtddWdn1swY|p%d}hd}||vri}|dvr=t||d <n2|d krN|durGdnt||d <n!|d kr_|durXdnt||d <n|d kro|duridnt||d <||j d i|IdHdSdS)aRuntime updates via key/value pair. .. deprecated:: 0.0.104 Use ``TTSUpdateSettingsFrame(delta=HumeTTSService.Settings(...))`` instead. Args: key: The name of the setting to update. Recognized keys are: - "voice_id" - "description" - "speed" - "trailing_silence" value: The new value for the setting. alwaysz_'update_setting' is deprecated, use 'TTSUpdateSettingsFrame(delta=self.Settings(...))' instead.) stacklevelN>r'r;r4r&r()r4r;r;r&r'r(r!) warningscatch_warnings simplefilterwarnDeprecationWarninglowerr-r/_update_settingsrI)rUrkrlkey_l known_keysrVr!r!r"update_settings.    zHumeTTSService.update_settingtext context_idc Csbt|d|d|t|jjdd}|jjdur"|jj|d<|jjdur.|jj|d<|jjdur:|jj|d<tdi|}t d d }| |IdHzzd |_ |jjdur[d nd }d}|j j j|g|d|dgd2zj3dHW}t|dd} | r|IdHt| } |j | 7_ t|j |jkrt|j |jd|d} | Vd |_ t|tr|j} | jdkr|j| jjd} |j| jjd}t||}| | j!| fg|IdHqm6|j rt|j |jd|d} | Vd |_ |dkr||_Wn t"y}z|j#d||dIdHWYd}~nd}~wwW|IdHdSW|IdHdS|IdHw)aGenerate speech from text using Hume TTS with word timestamps. Args: text: The text to be synthesized. context_id: Unique identifier for this TTS context. Returns: An async generator that yields `Frame` objects, including `TTSStartedFrame`, `TTSAudioRawFrame`, `ErrorFrame`, and `TTSStoppedFrame`. z: Generating Hume TTS: [])id)r{r;Nr&r'r(pcm)typerB12rCTword) utterancesformat instant_moder include_timestamp_typesaudio)rr6 num_channelsr|g@@rzUnknown error occurred: ) error_msg exceptionr!)$rdebugrr1r;r&r'r(rrstart_tts_usage_metricsrSrRttssynthesize_json_streaminggetattrstop_ttfb_metricsbase64 b64decodelen chunk_sizerr6rir timestamprrTtimebeginendmaxrjr{ Exception push_error)rUr{r|utterance_kwargs utterancepcm_fmtr utterance_durationchunk audio_b64 pcm_bytesr\rword_start_time word_end_timeer!r!r"run_ttss                *&"zHumeTTSService.run_tts)!r)r*r+r,rrIr.rr2rGrr-intrMboolr[rr]r^r rar rer DOWNSTREAMr rhrrzrrr __classcell__r!r!rXr"r0Bs@  U   &(r0)5r,rrDrq dataclassesrrtypingrrrrNlogururpydanticrrr pipecat_versionpipecat.frames.framesr r r r rrr"pipecat.processors.frame_processorrpipecat.services.settingsrrrpipecat.services.tts_servicer(pipecat.utils.tracing.service_decoratorsrhumerhume.ttsrrrhume.tts.typesrModuleNotFoundErrorrerrorrrGrPrr0r!r!r!r"s@   $