qivdZddlZddlZddlmZmZmZmZmZm Z ddl m Z m Z m Z Gdde ZGdde ZGd d e ZGd d e ZGd de ZGdde ZGdde ZGdde ZGdde ZGdde ZGdde ZGddeZGddeZGdd eZGd!d"eZGd#d$eZGd%d&eZGd'd(eZGd)d*eZ Gd+d,eZ!Gd-d.eZ"Gd/d0e Z#Gd1d2e#Z$Gd3d4e#Z%Gd5d6e#Z&Gd7d8e#Z'Gd9d:e#Z(Gd;de#Z*Gd?d@e#Z+GdAdBe#Z,GdCdDe#Z-GdEdFe#Z.GdGdHe#Z/GdIdJe#Z0GdKdLe#Z1GdMdNe#Z2GdOdPe#Z3GdQdRe#Z4GdSdTe#Z5GdUdVe#Z6GdWdXe#Z7GdYdZe#Z8Gd[d\e#Z9Gd]d^e#Z:Gd_d`e#Z;Gdadbe#Z<Gdcdde#Z=Gdedfe#Z>Gdgdhe#Z?Gdidje#Z@Gdkdle#ZAGdmdne ZBGdodpe ZCGdqdre ZDidse@dte$due%dve&dwe>dxe?dye<dze=d{e'd|e(d}e)d~e*de+de,de-de.de/e0e1e2e3e4e5e6e7e8e9e:e;eAd ZEdZFy)zGEvent models and data structures for OpenAI Realtime API communication.N)AnyDictListLiteralOptionalUnion) BaseModel ConfigDictFieldczeZdZUdZdZeed<eeed<eeed< ddeedeedeeffd ZxZ S)InputAudioTranscriptionz/Configuration for audio transcription settings.gpt-4o-transcribemodellanguagepromptc*t||||y)a Initialize InputAudioTranscription. Args: model: Transcription model to use (e.g., "gpt-4o-transcribe", "whisper-1"). language: Optional language code for transcription. prompt: Optional transcription hint text. )rrrN)super__init__)selfrrr __class__s ^/opt/pipecat/venv/lib/python3.12/site-packages/pipecat/services/openai_realtime_beta/events.pyrz InputAudioTranscription.__init__s uxG)rNN) __name__ __module__ __qualname____doc__rstr__annotations__rr __classcell__rs@rr r sf9$E3$sm SM 3"& $ H} H3- H H Hrr cheZdZUdZdZeeded<dZee ed<dZ ee ed<dZ ee ed <y ) TurnDetectionaServer-side voice activity detection configuration. Parameters: type: Detection type, must be "server_vad". threshold: Voice activity detection threshold (0.0-1.0). Defaults to 0.5. prefix_padding_ms: Padding before speech starts in milliseconds. Defaults to 300. silence_duration_ms: Silence duration to detect speech end in milliseconds. Defaults to 800. server_vadtypeg? thresholdi,prefix_padding_msi silence_duration_msN) rrrrr$rrrr%floatr&intr'rrr"r"+sI-9D(7<( )8!$Ix$'*x}*),#,rr"cneZdZUdZdZeeded<dZeeded<dZ ee ed<dZ ee ed<y) SemanticTurnDetectionaSemantic-based turn detection configuration. Parameters: type: Detection type, must be "semantic_vad". eagerness: Turn detection eagerness level. Can be "low", "medium", "high", or "auto". create_response: Whether to automatically create responses on turn detection. interrupt_response: Whether to interrupt ongoing responses on turn detection. semantic_vadr$N)lowmediumhighauto eagernesscreate_responseinterrupt_response) rrrrr$rrrr2r3boolr4r*rrr,r,;sO/=D(7>* +E#'K%'GKsGEN/B)C DKrr;c^eZdZUdZeded<dZeeed<dZ eeed<dZ eeed<y) ItemContenta Content within a conversation item. Parameters: type: Content type (text, audio, input_text, or input_audio). text: Text content for text-based items. audio: Base64-encoded audio data for audio items. transcript: Transcribed text for audio items. )r=r> input_text input_audior$Nr=r> transcript) rrrrrrr=rrr>rXr*rrrUrU}s? > ??D(3-E8C= $J $rrUceZdZUdZedZeed<dZe e ded<e ded <dZ e e d ed <dZ e e d ed <dZ e eeed<dZe eed<dZe eed<dZe eed<dZe eed<y)ConversationItemaA conversation item in the realtime session. Parameters: id: Unique identifier for the item, auto-generated if not provided. object: Object type identifier for the realtime API. type: Item type (message, function_call, or function_call_output). status: Current status of the item. role: Speaker role for message items (user, assistant, or system). content: Content list for message items. call_id: Function call identifier for function_call items. name: Function name for function_call items. arguments: Function arguments as JSON string for function_call items. output: Function output as JSON string for function_call_output items. cPttjjSN)ruuiduuid4hexr*rrzConversationItem.sC 0@0@,Ardefault_factoryidNz realtime.itemobject)message function_callfunction_call_outputr$) completed in_progress incompletestatus)user assistantsystemrolecontentcall_idname argumentsoutput)rrrrr rcrrrdrrrkrorprrUrqrrrsrtr*rrrZrZs $ABBB15FHW_- .5 D EEJNFHWEF GN=AD(789 :A+/GXd;' (/!GXc]!D(3-#Ix}# FHSM rrZc,eZdZUdZeed<eded<y)RealtimeConversationzA realtime conversation session. Parameters: id: Unique identifier for the conversation. object: Object type identifier, always "realtime.conversation". rczrealtime.conversationrdN)rrrrrrrr*rrrvrvs G + ,,rrvceZdZUdZddgZeeeded<dZ ee ed<dZ ee ed<dZ eed ed <e e Zeeeed <dZeed ed<dZeeed<dZeeeedfed<y)ResponsePropertiesaFProperties for configuring assistant responses. Parameters: modalities: Output modalities for the response. Defaults to ["audio", "text"]. instructions: Specific instructions for this response. voice: Voice ID for text-to-speech in this response. output_audio_format: Audio format for this response. tools: Available tools for this response. tool_choice: Tool usage strategy for this response. temperature: Sampling temperature for this response. max_response_output_tokens: Maximum tokens for this response. r>r=r<r?Nr@rArBrGrarLrMrPrQrRrS)rrrrr?rrrrr@rrArGr listrLrrPrQr(rSrr)r*rrrxrxs =DV;LJgo678L"&L(3-&E8C=PT'*K"LMT"'"=E8DJ =AEK'"<=>E#'K%'GKsGEN/B)C DKrrxcbeZdZUdZeed<dZeeed<eed<dZeeed<dZ eeed<y) RealtimeErrora>Error information from the realtime API. Parameters: type: Error type identifier. code: Specific error code. message: Human-readable error message. param: Parameter name that caused the error, if applicable. event_id: Event ID associated with the error, if applicable. r$codereNparamevent_id) rrrrrrr}rr~rr*rrr{r{s= ID(3- LE8C="Hhsm"rr{c0eZdZUdZedZeed<y) ClientEventzBase class for client events sent to the realtime API. Parameters: event_id: Unique identifier for the event, auto-generated if not provided. c<ttjSr\)rr]r^r*rrr`zClientEvent.s#djjl2CrrarN)rrrrr rrrr*rrrrs *CDHcDrrcReZdZUdZdZeded<eed<dee e fffd Z xZ S)SessionUpdateEventzEvent to update session properties. Parameters: type: Event type, always "session.update". session: Updated session properties. zsession.updater$sessionreturncXt||i|}d|dvr|dddurd|dd<|S)a`Serialize the event to a dictionary. Handles special serialization for turn_detection where False becomes null. Args: *args: Positional arguments passed to parent model_dump. **kwargs: Keyword arguments passed to parent model_dump. Returns: Dictionary representation of the event. rKrFN)r model_dump)rargskwargsdumprs rrzSessionUpdateEvent.model_dumpsMw!4262 tI .I/0E948Y 01 r) rrrrr$rrr;rrrrrr s@rrrs9'7D'" #6 T#s(^rrc0eZdZUdZdZeded<eed<y)InputAudioBufferAppendEventzEvent to append audio data to the input buffer. Parameters: type: Event type, always "input_audio_buffer.append". audio: Base64-encoded audio data to append. zinput_audio_buffer.appendr$r>Nrrrrr$rrrr*rrrrs2MD'- .L Jrrc&eZdZUdZdZeded<y)InputAudioBufferCommitEventzEvent to commit the current input audio buffer. Parameters: type: Event type, always "input_audio_buffer.commit". zinput_audio_buffer.commitr$Nrrrrr$rrr*rrrr s 2MD'- .Lrrc&eZdZUdZdZeded<y)InputAudioBufferClearEventzyEvent to clear the input audio buffer. Parameters: type: Event type, always "input_audio_buffer.clear". zinput_audio_buffer.clearr$Nrr*rrrr*s 1KD', -JrrcDeZdZUdZdZeded<dZee ed<e ed<y)ConversationItemCreateEventzEvent to create a new conversation item. Parameters: type: Event type, always "conversation.item.create". previous_item_id: ID of the item to insert after, if any. item: The conversation item to create. zconversation.item.creater$Nprevious_item_iditem) rrrrr$rrrrrrZr*rrrr4s/1KD', -J&*hsm* rrcDeZdZUdZdZeded<eed<eed<eed<y)ConversationItemTruncateEventaIEvent to truncate a conversation item's audio content. Parameters: type: Event type, always "conversation.item.truncate". item_id: ID of the item to truncate. content_index: Index of the content to truncate within the item. audio_end_ms: End time in milliseconds for the truncated audio. zconversation.item.truncater$item_id content_index audio_end_msN) rrrrr$rrrr)r*rrrrBs+3OD'. /N Lrrc0eZdZUdZdZeded<eed<y)ConversationItemDeleteEventzEvent to delete a conversation item. Parameters: type: Event type, always "conversation.item.delete". item_id: ID of the item to delete. zconversation.item.deleter$rNrr*rrrrRs1KD', -J Lrrc0eZdZUdZdZeded<eed<y)ConversationItemRetrieveEventzEvent to retrieve a conversation item by ID. Parameters: type: Event type, always "conversation.item.retrieve". item_id: ID of the item to retrieve. zconversation.item.retriever$rNrr*rrrr^s3OD'. /N Lrrc:eZdZUdZdZeded<dZee ed<y)ResponseCreateEventzEvent to create a new assistant response. Parameters: type: Event type, always "response.create". response: Optional response configuration properties. zresponse.creater$Nresponse) rrrrr$rrrrrxr*rrrrjs)(9D'# $8-1Hh)*1rrc&eZdZUdZdZeded<y)ResponseCancelEventzyEvent to cancel the current assistant response. Parameters: type: Event type, always "response.cancel". zresponse.cancelr$Nrr*rrrrvs (9D'# $8rrc8eZdZUdZedZeed<eed<y) ServerEventzBase class for server events received from the realtime API. Parameters: event_id: Unique identifier for the event. type: Type of the server event. T)arbitrary_types_allowedrr$N)rrrrr model_configrrr*rrrrsd;LM Irrc,eZdZUdZeded<eed<y)SessionCreatedEventzEvent indicating a session has been created. Parameters: type: Event type, always "session.created". session: The created session properties. session.createdr$rNrrrrrrr;r*rrrr # $$ rrc,eZdZUdZeded<eed<y)SessionUpdatedEventzEvent indicating a session has been updated. Parameters: type: Event type, always "session.updated". session: The updated session properties. session.updatedr$rNrr*rrrrrrrc,eZdZUdZeded<eed<y)ConversationCreatedzEvent indicating a conversation has been created. Parameters: type: Event type, always "conversation.created". conversation: The created conversation. conversation.createdr$ conversationN)rrrrrrrvr*rrrrs ( ))&&rrc@eZdZUdZeded<dZeeed<e ed<y)ConversationItemCreatedzEvent indicating a conversation item has been created. Parameters: type: Event type, always "conversation.item.created". previous_item_id: ID of the previous item, if any. item: The created conversation item. conversation.item.createdr$Nrr) rrrrrrrrrrZr*rrrrs* - ..&*hsm* rrc@eZdZUdZeded<eed<eed<eed<y),ConversationItemInputAudioTranscriptionDeltaaOEvent containing incremental input audio transcription. Parameters: type: Event type, always "conversation.item.input_audio_transcription.delta". item_id: ID of the conversation item being transcribed. content_index: Index of the content within the item. delta: Incremental transcription text. 1conversation.item.input_audio_transcription.deltar$rrdeltaNrrrrrrrr)r*rrrrs% E FF L Jrrc@eZdZUdZeded<eed<eed<eed<y)0ConversationItemInputAudioTranscriptionCompletedaXEvent indicating input audio transcription is complete. Parameters: type: Event type, always "conversation.item.input_audio_transcription.completed". item_id: ID of the conversation item that was transcribed. content_index: Index of the content within the item. transcript: Complete transcription text. 5conversation.item.input_audio_transcription.completedr$rrrXNrr*rrrrs% I JJ LOrrc@eZdZUdZeded<eed<eed<eed<y)-ConversationItemInputAudioTranscriptionFaileda`Event indicating input audio transcription failed. Parameters: type: Event type, always "conversation.item.input_audio_transcription.failed". item_id: ID of the conversation item that failed transcription. content_index: Index of the content within the item. error: Error details for the transcription failure. 2conversation.item.input_audio_transcription.failedr$rrerrorN) rrrrrrrr)r{r*rrrrs& F GG L rrc@eZdZUdZeded<eed<eed<eed<y)ConversationItemTruncatedaKEvent indicating a conversation item has been truncated. Parameters: type: Event type, always "conversation.item.truncated". item_id: ID of the truncated conversation item. content_index: Index of the content within the item. audio_end_ms: End time in milliseconds for the truncated audio. conversation.item.truncatedr$rrrNrr*rrrrs& / 00 Lrrc,eZdZUdZeded<eed<y)ConversationItemDeletedzEvent indicating a conversation item has been deleted. Parameters: type: Event type, always "conversation.item.deleted". item_id: ID of the deleted conversation item. conversation.item.deletedr$rN)rrrrrrrr*rrrrs - .. Lrrc,eZdZUdZeded<eed<y)ConversationItemRetrievedzEvent containing a retrieved conversation item. Parameters: type: Event type, always "conversation.item.retrieved". item: The retrieved conversation item. conversation.item.retrievedr$rN)rrrrrrrZr*rrrrs / 00 rrc,eZdZUdZeded<ded<y)ResponseCreatedzEvent indicating an assistant response has been created. Parameters: type: Event type, always "response.created". response: The created response object. response.createdr$ResponserNrrrrrrr*rrrrs $ %%rrc,eZdZUdZeded<ded<y) ResponseDonezEvent indicating an assistant response is complete. Parameters: type: Event type, always "response.done". response: The completed response object. response.doner$rrNrr*rrrr)s / ""rrc@eZdZUdZeded<eed<eed<eed<y)ResponseOutputItemAddedaEvent indicating an output item has been added to a response. Parameters: type: Event type, always "response.output_item.added". response_id: ID of the response. output_index: Index of the output item. item: The added conversation item. response.output_item.addedr$ response_id output_indexrN rrrrrrrr)rZr*rrrr5s' . // rrc@eZdZUdZeded<eed<eed<eed<y)ResponseOutputItemDoneaEvent indicating an output item is complete. Parameters: type: Event type, always "response.output_item.done". response_id: ID of the response. output_index: Index of the output item. item: The completed conversation item. response.output_item.doner$rrrNrr*rrrrEs' - .. rrcTeZdZUdZeded<eed<eed<eed<eed<eed<y ) ResponseContentPartAddedarEvent indicating a content part has been added to a response. Parameters: type: Event type, always "response.content_part.added". response_id: ID of the response. item_id: ID of the conversation item. output_index: Index of the output item. content_index: Index of the content part. part: The added content part. response.content_part.addedr$rrrrpartN rrrrrrrr)rUr*rrrrUs2  / 00 L rrcTeZdZUdZeded<eed<eed<eed<eed<eed<y ) ResponseContentPartDoneadEvent indicating a content part is complete. Parameters: type: Event type, always "response.content_part.done". response_id: ID of the response. item_id: ID of the conversation item. output_index: Index of the output item. content_index: Index of the content part. part: The completed content part. response.content_part.doner$rrrrrNrr*rrrris2  . // L rrcTeZdZUdZeded<eed<eed<eed<eed<eed<y ) ResponseTextDeltaabEvent containing incremental text from a response. Parameters: type: Event type, always "response.text.delta". response_id: ID of the response. item_id: ID of the conversation item. output_index: Index of the output item. content_index: Index of the content part. delta: Incremental text content. response.text.deltar$rrrrrNrr*rrrr}s1  ' (( L JrrcTeZdZUdZeded<eed<eed<eed<eed<eed<y ) ResponseTextDoneaUEvent indicating text content is complete. Parameters: type: Event type, always "response.text.done". response_id: ID of the response. item_id: ID of the conversation item. output_index: Index of the output item. content_index: Index of the content part. text: Complete text content. response.text.doner$rrrrr=Nrr*rrrrs1  & '' L IrrcTeZdZUdZeded<eed<eed<eed<eed<eed<y ) ResponseAudioTranscriptDeltaa}Event containing incremental audio transcript from a response. Parameters: type: Event type, always "response.audio_transcript.delta". response_id: ID of the response. item_id: ID of the conversation item. output_index: Index of the output item. content_index: Index of the content part. delta: Incremental transcript text. response.audio_transcript.deltar$rrrrrNrr*rrrrs1  3 44 L JrrcTeZdZUdZeded<eed<eed<eed<eed<eed<y ) ResponseAudioTranscriptDoneanEvent indicating audio transcript is complete. Parameters: type: Event type, always "response.audio_transcript.done". response_id: ID of the response. item_id: ID of the conversation item. output_index: Index of the output item. content_index: Index of the content part. transcript: Complete transcript text. response.audio_transcript.doner$rrrrrXNrr*rrrrs1  2 33 LOrrcTeZdZUdZeded<eed<eed<eed<eed<eed<y ) ResponseAudioDeltaavEvent containing incremental audio data from a response. Parameters: type: Event type, always "response.audio.delta". response_id: ID of the response. item_id: ID of the conversation item. output_index: Index of the output item. content_index: Index of the content part. delta: Base64-encoded incremental audio data. response.audio.deltar$rrrrrNrr*rrrrs1  ( )) L JrrcJeZdZUdZeded<eed<eed<eed<eed<y) ResponseAudioDonea2Event indicating audio content is complete. Parameters: type: Event type, always "response.audio.done". response_id: ID of the response. item_id: ID of the conversation item. output_index: Index of the output item. content_index: Index of the content part. response.audio.doner$rrrrNrr*rrrrs, ' (( LrrcTeZdZUdZeded<eed<eed<eed<eed<eed<y ) "ResponseFunctionCallArgumentsDeltaa~Event containing incremental function call arguments. Parameters: type: Event type, always "response.function_call_arguments.delta". response_id: ID of the response. item_id: ID of the conversation item. output_index: Index of the output item. call_id: ID of the function call. delta: Incremental function arguments as JSON. &response.function_call_arguments.deltar$rrrrqrNrr*rrrrs0  : ;; L L JrrcTeZdZUdZeded<eed<eed<eed<eed<eed<y ) !ResponseFunctionCallArgumentsDoneaEvent indicating function call arguments are complete. Parameters: type: Event type, always "response.function_call_arguments.done". response_id: ID of the response. item_id: ID of the conversation item. output_index: Index of the output item. call_id: ID of the function call. arguments: Complete function arguments as JSON string. %response.function_call_arguments.doner$rrrrqrsNrr*rrrrs0  9 :: L LNrrc6eZdZUdZeded<eed<eed<y)InputAudioBufferSpeechStartedaEvent indicating speech has started in the input audio buffer. Parameters: type: Event type, always "input_audio_buffer.speech_started". audio_start_ms: Start time of speech in milliseconds. item_id: ID of the associated conversation item. !input_audio_buffer.speech_startedr$audio_start_msrNrrrrrrr)rr*rrrrs  5 66 Lrrc6eZdZUdZeded<eed<eed<y)InputAudioBufferSpeechStoppeda Event indicating speech has stopped in the input audio buffer. Parameters: type: Event type, always "input_audio_buffer.speech_stopped". audio_end_ms: End time of speech in milliseconds. item_id: ID of the associated conversation item. !input_audio_buffer.speech_stoppedr$rrNrr*rrrr)s  5 66 Lrrc@eZdZUdZeded<dZeeed<eed<y)InputAudioBufferCommittedaEvent indicating the input audio buffer has been committed. Parameters: type: Event type, always "input_audio_buffer.committed". previous_item_id: ID of the previous item, if any. item_id: ID of the committed conversation item. input_audio_buffer.committedr$Nrr) rrrrrrrrrr*rrrr7s) 0 11&*hsm* Lrrc"eZdZUdZeded<y)InputAudioBufferClearedzEvent indicating the input audio buffer has been cleared. Parameters: type: Event type, always "input_audio_buffer.cleared". input_audio_buffer.clearedr$Nrr*rrr r Es . //rr c,eZdZUdZeded<eed<y) ErrorEventzEvent indicating an error occurred. Parameters: type: Event type, always "error". error: Error details. rr$N)rrrrrrr{r*rrrrOs '  rrc<eZdZUdZeded<eeee fed<y)RateLimitsUpdatedzEvent indicating rate limits have been updated. Parameters: type: Event type, always "rate_limits.updated". rate_limits: List of rate limit information. rate_limits.updatedr$ rate_limitsN) rrrrrrrrrrr*rrrr[s( ' ((d38n%%rrc`eZdZUdZedZdZeee d<dZ eee d<dZ eee d<y) TokenDetailszDetailed token usage information. Parameters: cached_tokens: Number of cached tokens used. Defaults to 0. text_tokens: Number of text tokens used. Defaults to 0. audio_tokens: Number of audio tokens used. Defaults to 0. allow)extrar cached_tokens text_tokens audio_tokensN) rrrrr rrrr)rrrr*rrrrgs=G,L#$M8C=$!"K#""#L(3-#rrcDeZdZUdZeed<eed<eed<eed<eed<y)UsageaeToken usage statistics for a response. Parameters: total_tokens: Total number of tokens used. input_tokens: Number of input tokens used. output_tokens: Number of output tokens used. input_token_details: Detailed breakdown of input token usage. output_token_details: Detailed breakdown of output token usage. total_tokens input_tokens output_tokensinput_token_detailsoutput_token_detailsN)rrrrr)rrr*rrrrws'%%&&rrcjeZdZUdZeed<eded<eded<eed<ee ed<d Z e e ed <y ) raxA complete assistant response. Parameters: id: Unique identifier for the response. object: Object type, always "realtime.response". status: Current status of the response. status_details: Additional status information. output: List of conversation items in the response. usage: Token usage statistics for the response. rczrealtime.responserd)rhrirj cancelledfailedrkstatus_detailsrtNusage) rrrrrrrrrrZr%rrr*rrrrsF  G ' (( S TT ! ""!E8E?!rrrrrrr r rrrrrrrrrrr) rrrrrrrrrrrrrc tj|}|d}|tvrtd|t|j |S#t$r}t|d|d}~wwxYw)a Parse a server event from JSON string. Args: str: JSON string containing the server event. Returns: Parsed server event object of the appropriate type. Raises: Exception: If the event type is unimplemented or parsing fails. r$z!Unimplemented server event type: z N)jsonloads_server_event_types Exceptionmodel_validate)revent event_typees rparse_server_eventr/su* 36] 0 0? |LM M":.==eDD *1#U3%())*sAA A(A##A()Grr'r]typingrrrrrrpydanticr r r r r"r,r7r;rUrZrvrxr{rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr rrrrrr)r/r*rrr2sN <<11HiH. -I - .I . 7y7 L LP %) % !y!< -9 -LL6#I#.E)EB + M+MKK +  K  +  K  2+ 29+9 )  +  +  '+ ' k  ;  {  K    k    k  ;  k  [  {(k( ({(;(+(( $( ( K  K   0k0   & & $9 $ 'I'$"y"( Z**/  #$=  !"9 ()F()F !889e<=m9:g"#< !8"#< !"\#$#:!7#;"9,*'C&A.,.P-N,=D*r