o i_( @s2dZddlZddlmZddlmZddlmZmZm Z m Z ddl Z ddl m Z ddlmZmZmZddlmZdd lmZdd lmZzdd lmZdd lmZWn eyrZze d ee dededZ[wweGdddeZ GdddeZ!eGdddeZ"GdddeZ#dS)z!Piper TTS service implementation.N) dataclass)Path)AnyAsyncGenerator AsyncIteratorOptional)logger) ErrorFrameFrameTTSStoppedFrame) TTSSettings) TTSService) traced_tts) PiperVoice)download_voicez Exception: zCIn order to use Piper, you need to `pip install pipecat-ai[piper]`.zMissing module: c@eZdZdZdS)PiperTTSSettingszSettings for PiperTTSService.N__name__ __module__ __qualname____doc__rrN/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/piper/tts.pyr#rc seZdZUdZeZeed<dddddddeedee de d e d eef fd d Z d e fddZ ded e eefffdd Zededed eedffddZZS)PiperTTSServicezPiper TTS service implementation. Provides local text-to-speech synthesis using Piper voice models. Automatically downloads voice models if not already present and resamples audio output to match the configured sample rate. _settingsNF)voice_id download_dirforce_redownloaduse_cudasettingsrrrr r!c  s|jdddd}|dur|dd||_|dur||tjddd|d||p0t}|jj}|d} t|| } | sTt d|d t |||d t d |d | t j| |d |_t d|d dS)aInitialize the Piper TTS service. Args: voice_id: Piper voice model identifier (e.g. `en_US-ryan-high`). .. deprecated:: 0.0.105 Use ``settings=PiperTTSService.Settings(voice=...)`` instead. download_dir: Directory for storing voice model files. Defaults to the current working directory. force_redownload: Re-download the voice model even if it already exists. use_cuda: Use CUDA for GPU-accelerated inference. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional arguments passed to the parent `TTSService`. Nmodelvoicelanguagerr$Tpush_start_framepush_stop_framesr!z.onnxzDownloading Piper 'z' model)rzLoading Piper 'z ' model from )r zLoaded Piper 'r)Settings"_warn_init_param_moved_to_settingsr$ apply_updatesuper__init__rcwdrexistsrdebugrrload_voice) selfrrrr r!kwargsdefault_settingsr2 model_filemodel_path_resolved __class__rrr-5s.     zPiperTTSService.__init__returncCdSzCheck if this service can generate processing metrics. Returns: True, as Piper service supports metrics generation. Trr3rrrcan_generate_metricstz$PiperTTSService.can_generate_metricsdeltacs*t|IdH}|s|S|||S)zgApply a settings delta. Settings are stored but not applied to the active connection. N)r,_update_settings _warn_unhandled_updated_settings)r3r@changedr8rrrA|s  z PiperTTSService._update_settingstext context_idc sXdddttffdd }t|d|dz}z-||IdH|j||j||jjj |d 2z3dHW}| IdH|Vq66Wn%t yn}zt |d |t d |d VWYd}~nd}~wwWt|d |d| IdHdSWt|d |d| IdHdSt|d |d| IdHw)aGenerate speech from text using Piper. Args: text: The text to convert to speech. context_id: Unique identifier for this TTS context. Yields: Frame: Audio frames containing the synthesized speech and status frames. cSs zt|WStyYdSwN)next StopIteration)itrrr async_nexts   z+PiperTTSService.run_tts..async_nextr:cs, t|IdH}|durdS|jVqrF)asyncio to_threadaudio_int16_bytes)iteratoritemrJrrasync_iteratorsz/PiperTTSService.run_tts..async_iterator: Generating TTS []N)in_sample_raterEz exception: Unknown error occurred: errorz: Finished TTS [)rbytesrr0start_tts_usage_metrics"_stream_audio_frames_from_iteratorr2 synthesizeconfig sample_ratestop_ttfb_metrics ExceptionrWr )r3rDrErQframeerrPrrun_ttss6  zPiperTTSService.run_tts)rrrrrr)__annotations__rstrrboolr-r>dictrrArrr rb __classcell__rrr8rr*s0 ? (rc@r)PiperHttpTTSSettingsz!Settings for PiperHttpTTSService.Nrrrrrrhrrhc seZdZUdZeZeed<ddddedej de ede effd d Z d e fd d Z ededed eedffddZZS)PiperHttpTTSServicezPiper HTTP TTS service implementation. Provides integration with Piper's HTTP TTS server for text-to-speech synthesis. Supports streaming audio generation with configurable sample rates and automatic WAV header removal. rN)rr!base_urlaiohttp_sessionrr!c s|jdddd}|dur|dd||_|dur||tjd dd|d||dr;td|dd }||_ ||_ dS) asInitialize the Piper TTS service. Args: base_url: Base URL for the Piper TTS HTTP server. aiohttp_session: aiohttp ClientSession for making HTTP requests. voice_id: Piper voice model identifier (e.g. `en_US-ryan-high`). .. deprecated:: 0.0.105 Use ``settings=PiperHttpTTSService.Settings(voice=...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional arguments passed to the parent TTSService. Nr"rr$Tr&/z0Base URL ends with a slash, this is not allowed.r) r)r*r$r+r,r-endswithrwarning _base_url_session)r3rjrkrr!r4r5r8rrr-s$      zPiperHttpTTSService.__init__r:cCr;r<rr=rrrr>r?z(PiperHttpTTSService.can_generate_metricsrDrEc Cst|d|dddi}zz||jjd}|jj|j||d4IdHi}|jdkr]|IdH}t d |jd |d d Vt |d V WdIdHWW| IdHdS| |IdH|j }|j|j|d|d2z3dHW}| IdH|Vqt6WdIdHn 1IdHswYWnty} zt d| d VWYd} ~ nd} ~ wwW| IdHdSW| IdHdS| IdHw)a Generate speech from text using Piper's HTTP 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 and status frames. rRrSz Content-Typezapplication/json)rDr$)jsonheadersNzError getting audio (status: z , error: )rV)rET)strip_wav_headerrErU)rr0rr$rqpostrpstatusrDr r r^rY chunk_sizerZcontent iter_chunkedr_) r3rDrErsdataresponserW CHUNK_SIZEr`rarrrrb sL    ("zPiperHttpTTSService.run_tts)rrrrrhr)rcrdaiohttp ClientSessionrr-rer>rrr rbrgrrr8rris$ 3(ri)$rrK dataclassesrpathlibrtypingrrrrrlogururpipecat.frames.framesr r r pipecat.services.settingsr pipecat.services.tts_servicer (pipecat.utils.tracing.service_decoratorsrpiperrpiper.download_voicesrModuleNotFoundErrorrarWr_rrrhrirrrrs6