o ir$@sUdZddlmZmZddlmZmZmZmZddl m Z ddl m Z m Z ddlmZddlmZmZmZmZddlmZmZmZdd lmZdd lmZed Zd d dddddddddddd Zeeefe d<eGdddeZ!GdddeZ"dS)zOpenAI text-to-speech service implementation. This module provides integration with OpenAI's text-to-speech API for generating high-quality synthetic speech from text input. ) dataclassfield)AsyncGeneratorDictLiteralOptional)logger) AsyncOpenAIBadRequestError) BaseModel) ErrorFrameFrame StartFrameTTSAudioRawFrame) NOT_GIVEN TTSSettings _NotGiven) TTSService) traced_tts) alloyashballadcedarcoralechofablemarinnovaonyxsageshimmerverserrrrrrrrrrrr r! VALID_VOICESc@sFeZdZUdZedddZeeBed<edddZ e eBed<dS) OpenAITTSSettingszSettings for OpenAITTSService. Parameters: instructions: Instructions to guide voice synthesis behavior. speed: Voice speed control (0.25 to 4.0, default 1.0). cCtSNrr'r'O/home/ubuntu/.local/lib/python3.10/site-packages/pipecat/services/openai/tts.pyHzOpenAITTSSettings.)default_factory instructionscCr$r%r&r'r'r'r(r)Ir*speedN) __name__ __module__ __qualname____doc__rr,strr__annotations__r-floatr'r'r'r(r#?s r#cseZdZUdZeZeed<dZGdddeZ dddddddddd de e d e e d e e d e e d e e d e e de e de e de effddZdefddZdeffdd Zede de deedffddZZS)OpenAITTSServiceaOpenAI Text-to-Speech service that generates audio from text. This service uses the OpenAI TTS API to generate PCM-encoded audio at 24kHz. Supports multiple voice models and configurable parameters for high-quality speech synthesis with streaming audio output. _settingsi]c@s2eZdZUdZdZeeed<dZee ed<dS)zOpenAITTSService.InputParamsa?Input parameters for OpenAI TTS configuration. .. deprecated:: 0.0.105 Use ``settings=OpenAITTSService.Settings(...)`` instead. Parameters: instructions: Instructions to guide voice synthesis behavior. speed: Voice speed control (0.25 to 4.0, default 1.0). Nr,r-) r.r/r0r1r,rr2r3r-r4r'r'r'r( InputParamsYs  r7N) api_keybase_urlvoicemodel sample_rater,r-paramssettingsr8r9r:r;r<r,r-r=r>c  s|r||jkrtd|jd|d|jdddddd} |dur+|dd|| _|dur8|d d || _|durE|d d || _|durR|d d || _|duro|d | so|jdurf|j| _|jduro|j| _| durx| | t j d|d d | d| t ||d|_ dS)aInitialize OpenAI TTS service. Args: api_key: OpenAI API key for authentication. If None, uses environment variable. base_url: Custom base URL for OpenAI API. If None, uses default. voice: Voice ID to use for synthesis. Defaults to "alloy". .. deprecated:: 0.0.105 Use ``settings=OpenAITTSService.Settings(voice=...)`` instead. model: TTS model to use. Defaults to "gpt-4o-mini-tts". .. deprecated:: 0.0.105 Use ``settings=OpenAITTSService.Settings(model=...)`` instead. sample_rate: Output audio sample rate in Hz. If None, uses OpenAI's default 24kHz. instructions: Optional instructions to guide voice synthesis behavior. .. deprecated:: 0.0.105 Use ``settings=OpenAITTSService.Settings(instructions=...)`` instead. speed: Voice speed control (0.25 to 4.0, default 1.0). .. deprecated:: 0.0.105 Use ``settings=OpenAITTSService.Settings(speed=...)`` instead. params: Optional synthesis controls (acting instructions, speed, ...). .. deprecated:: 0.0.105 Use ``settings=OpenAITTSService.Settings(...)`` instead. settings: Runtime-updatable settings. When provided alongside deprecated parameters, ``settings`` values take precedence. **kwargs: Additional keyword arguments passed to TTSService. zOpenAI TTS only supports Hz sample rate. Current rate of Hz may cause issues.zgpt-4o-mini-ttsrN)r;r:languager,r-r:r;r,r-r=T)r<push_start_framepush_stop_framesr>)r8r9r')OPENAI_SAMPLE_RATErwarningSettings"_warn_init_param_moved_to_settingsr:r;r,r- apply_updatesuper__init__r _client) selfr8r9r:r;r<r,r-r=r>kwargsdefault_settings __class__r'r(rJgsV1         zOpenAITTSService.__init__returncCsdS)zCheck if this service can generate processing metrics. Returns: True, as OpenAI TTS service supports metrics generation. Tr')rLr'r'r(can_generate_metricssz%OpenAITTSService.can_generate_metricsframecsDt|IdH|j|jkr td|jd|jddSdS)z~Start the OpenAI TTS service. Args: frame: The start frame containing initialization parameters. NzOpenAI TTS requires r?r@)rIstartr<rDrrE)rLrSrOr'r(rTs  zOpenAITTSService.starttext context_idc Cst|d|dz||jjt|jjdd}|jjr$|jj|d<|jjr.|jj|d<|jj j j j di|4IdHt}|j dkru|IdH}t|d |j d |d td |j d |d d V WdIdHWdS||IdH|j}||2z3dHW}t|dkr|IdHt||jd|d}|Vq6WdIdHWdS1IdHswYWdSty} ztd| d VWYd} ~ dSd} ~ ww)aGenerate speech from text using OpenAI's TTS 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 data. z: Generating TTS []pcm)inputr;r:response_formatr,r-Nz error getting audio (status: z , error: )zError getting audio (status: )errorr)rVzUnknown error occurred: r')rdebugr6r;r"r:r,r-rKaudiospeechwith_streaming_responsecreate status_coderUr]r start_tts_usage_metrics chunk_size iter_byteslenstop_ttfb_metricsrr<r ) rLrUrV create_paramsrr] CHUNK_SIZEchunkrSer'r'r(run_ttssP       2 zOpenAITTSService.run_tts)r.r/r0r1r#rFr3rDr r7rr2intr4rJboolrRrrTrrr ro __classcell__r'r'rOr(r5LsL    e (r5N)#r1 dataclassesrrtypingrrrrlogururopenair r pydanticr pipecat.frames.framesr r rrpipecat.services.settingsrrrpipecat.services.tts_servicer(pipecat.utils.tracing.service_decoratorsr ValidVoicer"r2r3r#r5r'r'r'r(s<