qiz$UdZddlmZmZddlmZmZmZmZddl m Z ddl m Z m Z ddlmZddlmZmZmZmZddlmZmZmZmZdd lmZdd lmZed Zd d dddddddddddd Zee efe!d<eGddeZ"GddeZ#y)zOpenAI text-to-speech service implementation. This module provides integration with OpenAI's text-to-speech API for generating high-quality synthetic speech from text input. ) dataclassfield)AsyncGeneratorDictLiteralOptional)logger) AsyncOpenAIBadRequestError) BaseModel) ErrorFrameFrame StartFrameTTSAudioRawFrame) NOT_GIVEN TTSSettings _NotGiven_warn_deprecated_param) TTSService) traced_tts) alloyashballadcedarcoralechofablemarinnovaonyxsageshimmerverserrrrrrrrrr r!r"r# VALID_VOICEScZeZdZUdZedZeezed<edZ e ezed<y)OpenAITTSSettingszSettings for OpenAITTSService. Parameters: instructions: Instructions to guide voice synthesis behavior. speed: Voice speed control (0.25 to 4.0, default 1.0). ctSNrM/opt/pipecat/venv/lib/python3.12/site-packages/pipecat/services/openai/tts.pyzOpenAITTSSettings.Hs)r+)default_factory instructionsctSr(r)r*r+r,r-zOpenAITTSSettings.IsYr+speedN) __name__ __module__ __qualname____doc__rr/strr__annotations__r1floatr*r+r,r&r&?s2%*:K$LL# /L$5FGE59 Gr+r&ceZdZUdZeZeed<dZGddeZ dddddddddd de e d e e d e e d e e d e e d e e de e de e de effdZdefdZdeffd Zede de deedffdZxZS)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:eZdZUdZdZeeed<dZee ed<y)OpenAITTSService.InputParamsa7Input parameters for OpenAI TTS configuration. .. deprecated:: 0.0.105 Use ``settings=OpenAITTSSettings(...)`` instead. Parameters: instructions: Instructions to guide voice synthesis behavior. speed: Voice speed control (0.25 to 4.0, default 1.0). Nr/r1) r2r3r4r5r/rr6r7r1r8r*r+r, InputParamsr=Ys% '+ hsm*!%x%r+r>N) api_keybase_urlvoicemodel sample_rater/r1paramssettingsr?r@rArBrCr/r1rDrEc  r|r5||jk7r&tjd|jd|dtddddd} |t dtd|| _|t d td || _|t d td || _|t d td || _|Lt d t| s:|j|j| _|j|j| _| | j| t |,d|d d | d| t|||_ y)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=OpenAITTSSettings(voice=...)`` instead. model: TTS model to use. Defaults to "gpt-4o-mini-tts". .. deprecated:: 0.0.105 Use ``settings=OpenAITTSSettings(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=OpenAITTSSettings(instructions=...)`` instead. speed: Voice speed control (0.25 to 4.0, default 1.0). .. deprecated:: 0.0.105 Use ``settings=OpenAITTSSettings(speed=...)`` instead. params: Optional synthesis controls (acting instructions, speed, ...). .. deprecated:: 0.0.105 Use ``settings=OpenAITTSSettings(...)`` 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)rBrAlanguager/r1rArBr/r1rDT)rCpush_start_framepush_stop_framesrE)r?r@r*)OPENAI_SAMPLE_RATEr warningr&rrArBr/r1 apply_updatesuper__init__r _client) selfr?r@rArBrCr/r1rDrEkwargsdefault_settings __class__s r,rPzOpenAITTSService.__init__gshb ;$*A*AA NN+D,C,C+DE##.-/CE  -#     "7,=w G%*  "   "7,=w G%*  "  # ">3Dn U,8  )   "7,=w G%*  "   "8-> ?&&24:4G4G$1<<+-3\\$*    ) )( 3  #!!%    #7XF r+returncy)zCheck if this service can generate processing metrics. Returns: True, as OpenAI TTS service supports metrics generation. Tr*)rRs r,can_generate_metricsz%OpenAITTSService.can_generate_metricss r+framecKt||d{|j|jk7r1t j d|jd|jdyy7Ow)z~Start the OpenAI TTS service. Args: frame: The start frame containing initialization parameters. NzOpenAI TTS requires rGrH)rOstartrCrLr rM)rRrYrUs r,r[zOpenAITTSService.startsn gmE"""   t66 6 NN&t'>'>&?@##'#3#3"44HJ  7 #sA(A&AA(text context_idc Ktj|d|d ||jjt|jj dd}|jj r|jj |d<|jjr|jj|d<|jjjjjdi|4d{}|jdk7rr|jd{}tj|d |jd |d t!d |jd |d   dddd{y|j#|d{|j$}|j'|23d{}t)|dkDs|j+d{t-||j.d|}|O7 777w7S7.6dddd{7y#1d{7swYyxYw#t0$r} t!d|  Yd} ~ yd} ~ wwxYww)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)inputrBrAresponse_formatr/r1Nz error getting audio (status: z , error: )zError getting audio (status: )errorr)r]zUnknown error occurred: r*)r debugr;rBr$rAr/r1rQaudiospeechwith_streaming_responsecreate status_coder\rer start_tts_usage_metrics chunk_size iter_byteslenstop_ttfb_metricsrrCr ) rRr\r] create_paramsrre CHUNK_SIZEchunkrYes r,run_ttszOpenAITTSService.run_ttss-  v/vQ78& C--%dnn&:&:;#( M~~**040K0K n-~~##)-)=)= g&Ot||))00HHOO $ $==C'"#&&(NELL& >q}}oYW\V]]^_% =amm_IV[U\\]^ $ $ $224888!__ #$<< #;$$%5zA~"44666 08H8H!Xb c# + $+  $9$6$<# $ $ $ $ $, C%=aS#AB B B CsICH11G<2H15#HG?A H& H11H2H16I7H H !H-H 1H2H 5HHH#H<H1?HH1HH H H H1HH1IH."H% #H.*H1-I.H11 I:I III)r2r3r4r5r&Settingsr7rLr r>rr6intr8rPboolrXrr[rrrrw __classcell__)rUs@r,r:r:Ls/!H   &i &""&"&##%)&*!%(,04cG#cG3- cG } cG } cGc]cGsmcGcG%cG,-cGJd  1C#1C31C>%QU+;V1C1Cr+r:N)$r5 dataclassesrrtypingrrrrlogurur openair r pydanticr pipecat.frames.framesr rrrpipecat.services.settingsrrrrpipecat.services.tts_servicer(pipecat.utils.tracing.service_decoratorsr ValidVoicer$r6r7r&r:r*r+r,rs )::/ `_3?    "          ' d3 ?#"  H H  HGCzGCr+