o i @sxdZddlZddlmZddlmZddlmZmZddl Z ddl m Z ddl mZddlmZdd lmZmZmZdd lmZdd lmZdd lmZmZdd lmZz ddlZddlm Z Wn e!yZ"ze #de"e #de$de"dZ"["wweej%&dZ'dZ(dZ)de*defddZ+dedefddZ,dede*fdd Z-eGd!d"d"eZ.Gd#d$d$eZ/dS)%z4Kokoro TTS service implementation using kokoro-onnx.N) dataclass)Path)AsyncGeneratorOptional)logger) BaseModel)create_stream_resampler) ErrorFrameFrameTTSAudioRawFrame) TTSSettings) TTSService)Languageresolve_language) traced_tts)Kokoroz Exception: zEIn order to use Kokoro, you need to `pip install pipecat-ai[kokoro]`.zMissing module: z~/.cache/kokoro-onnxz_https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/kokoro-v1.0.onnxz^https://github.com/thewh1teagle/kokoro-onnx/releases/download/model-files-v1.0/voices-v1.0.binurldestcCstd|d|d|jjdddtj|ddd}|t|d}|jd d D]}| |q,Wd n1s>wYtd |d S) z1Download a file from a URL to a destination path.z Downloading z to z...T)parentsexist_oki,)streamtimeoutwbi ) chunk_sizeNz Downloaded ) rdebugparentmkdirrequestsgetraise_for_statusopen iter_contentwrite)rrrespfchunkr&O/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/kokoro/tts.py_download_file,s  r( model_path voices_pathcCs,|s tt||stt|dSdS)z)Download model files if they don't exist.N)existsr(KOKORO_MODEL_URLKOKORO_VOICES_URL)r)r*r&r&r'_ensure_model_files8s  r.languagereturncCsNtjdtjdtjdtjdtjdtjdtjdtjdtj dtj d i }t ||d d S) zConvert a Language enum to kokoro-onnx language code. Args: language: The Language enum value to convert. Returns: The corresponding kokoro-onnx locale code. zen-uszen-gbesfrhiitjaptzhT) use_base_code) rENEN_USEN_GBESFRHIITJAPTZHr)r/ LANGUAGE_MAPr&r&r'language_to_kokoro_language@s  rDc@seZdZdZdS)KokoroTTSSettingszSettings for KokoroTTSService.N)__name__ __module__ __qualname____doc__r&r&r&r'rEZsrEc seZdZUdZeZeed<GdddeZddddddde e de e d e e d e ed e ef fd d Z de fddZ dede fddZede de deedffddZZS)KokoroTTSServicezKokoro TTS service implementation. Provides local text-to-speech synthesis using kokoro-onnx. Automatically downloads model files on first use. _settingsc@s eZdZUdZejZeed<dS)zKokoroTTSService.InputParamsaInput parameters for Kokoro TTS configuration. .. deprecated:: 0.0.105 Use ``KokoroTTSService.Settings`` directly via the ``settings`` parameter instead. Parameters: language: Language to use for synthesis. r/N)rFrGrHrIrr9r/__annotations__r&r&r&r' InputParamsks  rMN)voice_idr)r*paramssettingsrNr)r*rOrPc  s|jddtjd}|dur|dd||_|dur%|d|s%|j|_|dur.||tjd dd|d||rAt |nt d}|rKt |nt d } t || t t |t | |_t|_dS) aAInitialize the Kokoro TTS service. Args: voice_id: Voice identifier to use for synthesis. .. deprecated:: 0.0.105 Use ``settings=KokoroTTSService.Settings(voice=...)`` instead. model_path: Path to the kokoro ONNX model file. Defaults to auto-downloaded file. voices_path: Path to the voices binary file. Defaults to auto-downloaded file. params: Configuration parameters for synthesis. .. deprecated:: 0.0.105 Use ``settings=KokoroTTSService.Settings(...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional arguments passed to parent `TTSService`. N)modelvoicer/rNrRrOT)push_start_framepush_stop_framesrPzkokoro-v1.0.onnxzvoices-v1.0.binr&)Settingsrr9"_warn_init_param_moved_to_settingsrRr/ apply_updatesuper__init__rKOKORO_CACHE_DIRr.rstr_kokoror _resampler) selfrNr)r*rOrPkwargsdefault_settings model_filevoices __class__r&r'rYws4     zKokoroTTSService.__init__r0cCsdS)z;Indicate that this service supports TTFB and usage metrics.Tr&)r^r&r&r'can_generate_metricssz%KokoroTTSService.can_generate_metricsr/cCst|S)zConvert a Language enum to kokoro-onnx language format. Args: language: The language to convert. Returns: The kokoro-onnx language code. )rD)r^r/r&r&r'language_to_service_languages z-KokoroTTSService.language_to_service_languagetext context_idc Cs t|d|dz{zK||IdH|jj||jj|jjdd}|2z/3dHW\}}|IdH|d t j  }|j |||jIdH}t||jd|dVq&6Wntys}ztd |d VWYd}~nd}~wwW|IdHdSW|IdHdS|IdHw) zSynthesize speech from text using kokoro-onnx. Uses the async streaming API to generate audio frames. Args: text: The text to synthesize. context_id: Unique identifier for this TTS context. z: Generating TTS []Ng?)rRlangspeedi)audio sample_rate num_channelsrhzUnknown error occurred: )error)rrstart_tts_usage_metricsr\ create_streamrKrRr/stop_ttfb_metricsastypenpint16tobytesr]resamplernr Exceptionr ) r^rgrhrsamplesrn audio_int16 audio_dataer&r&r'run_ttss8   "zKokoroTTSService.run_tts)rFrGrHrIrErUrLrrMrr[rYboolrerrfrrr r~ __classcell__r&r&rcr'rJas2 D (rJ)0rIos dataclassesrpathlibrtypingrrnumpyrulogururpydanticrpipecat.audio.utilsrpipecat.frames.framesr r r pipecat.services.settingsr pipecat.services.tts_servicer pipecat.transcriptions.languagerr(pipecat.utils.tracing.service_decoratorsrr kokoro_onnxrModuleNotFoundErrorr}rprypath expanduserrZr,r-r[r(r.rDrErJr&r&r&r'sB