Events

class pipecat.services.openai_realtime_beta.events.InputAudioTranscription(model='gpt-4o-transcribe', language=None, prompt=None)

Bases: BaseModel

Configuration for audio transcription settings.

Parameters:

• model (str)

• language (str | None)

• prompt (str | None)

model

Transcription model to use (e.g., “gpt-4o-transcribe”, “whisper-1”).

Type:

str

language

Optional language code for transcription.

Type:

str | None

prompt

Optional transcription hint text.

Type:

str | None

model: str

language: str | None

prompt: str | None

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.TurnDetection(*, type='server_vad', threshold=0.5, prefix_padding_ms=300, silence_duration_ms=800)

Bases: BaseModel

Parameters:

• type (Literal['server_vad'] | None)

• threshold (float | None)

• prefix_padding_ms (int | None)

• silence_duration_ms (int | None)

type: Literal['server_vad'] | None

threshold: float | None

prefix_padding_ms: int | None

silence_duration_ms: int | None

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.SemanticTurnDetection(*, type='semantic_vad', eagerness=None, create_response=None, interrupt_response=None)

Bases: BaseModel

Parameters:

• type (Literal['semantic_vad'] | None)

• eagerness (Literal['low', 'medium', 'high', 'auto'] | None)

• create_response (bool | None)

• interrupt_response (bool | None)

type: Literal['semantic_vad'] | None

eagerness: Literal['low', 'medium', 'high', 'auto'] | None

create_response: bool | None

interrupt_response: bool | None

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.InputAudioNoiseReduction(*, type)

Bases: BaseModel

Parameters:

type (Literal['near_field', 'far_field'] | None)

type: Literal['near_field', 'far_field'] | None

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.SessionProperties(*, modalities=None, instructions=None, voice=None, input_audio_format=None, output_audio_format=None, input_audio_transcription=None, input_audio_noise_reduction=None, turn_detection=None, tools=None, tool_choice=None, temperature=None, max_response_output_tokens=None)

Bases: BaseModel

Parameters:

• modalities (List[Literal['text', 'audio']] | None)

• instructions (str | None)

• voice (str | None)

• input_audio_format (Literal['pcm16', 'g711_ulaw', 'g711_alaw'] | None)

• output_audio_format (Literal['pcm16', 'g711_ulaw', 'g711_alaw'] | None)

• input_audio_transcription (InputAudioTranscription | None)

• input_audio_noise_reduction (InputAudioNoiseReduction | None)

• turn_detection (TurnDetection | SemanticTurnDetection | bool | None)

• tools (List[Dict] | None)

• tool_choice (Literal['auto', 'none', 'required'] | None)

• temperature (float | None)

• max_response_output_tokens (int | Literal['inf'] | None)

modalities: List[Literal['text', 'audio']] | None

instructions: str | None

voice: str | None

input_audio_format: Literal['pcm16', 'g711_ulaw', 'g711_alaw'] | None

output_audio_format: Literal['pcm16', 'g711_ulaw', 'g711_alaw'] | None

input_audio_transcription: InputAudioTranscription | None

input_audio_noise_reduction: InputAudioNoiseReduction | None

turn_detection: TurnDetection | SemanticTurnDetection | bool | None

tools: List[Dict] | None

tool_choice: Literal['auto', 'none', 'required'] | None

temperature: float | None

max_response_output_tokens: int | Literal['inf'] | None

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ItemContent(*, type, text=None, audio=None, transcript=None)

Bases: BaseModel

Parameters:

• type (Literal['text', 'audio', 'input_text', 'input_audio'])

• text (str | None)

• audio (str | None)

• transcript (str | None)

type: Literal['text', 'audio', 'input_text', 'input_audio']

text: str | None

audio: str | None

transcript: str | None

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ConversationItem(*, id=<factory>, object=None, type, status=None, role=None, content=None, call_id=None, name=None, arguments=None, output=None)

Bases: BaseModel

Parameters:

• id (str)

• object (Literal['realtime.item'] | None)

• type (Literal['message', 'function_call', 'function_call_output'])

• status (Literal['completed', 'in_progress', 'incomplete'] | None)

• role (Literal['user', 'assistant', 'system'] | None)

• content (List[ItemContent] | None)

• call_id (str | None)

• name (str | None)

• arguments (str | None)

• output (str | None)

id: str

object: Literal['realtime.item'] | None

type: Literal['message', 'function_call', 'function_call_output']

status: Literal['completed', 'in_progress', 'incomplete'] | None

role: Literal['user', 'assistant', 'system'] | None

content: List[ItemContent] | None

call_id: str | None

name: str | None

arguments: str | None

output: str | None

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.RealtimeConversation(*, id, object)

Bases: BaseModel

Parameters:

• id (str)

• object (Literal['realtime.conversation'])

id: str

object: Literal['realtime.conversation']

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseProperties(*, modalities=['audio', 'text'], instructions=None, voice=None, output_audio_format=None, tools=<factory>, tool_choice=None, temperature=None, max_response_output_tokens=None)

Bases: BaseModel

Parameters:

• modalities (List[Literal['text', 'audio']] | None)

• instructions (str | None)

• voice (str | None)

• output_audio_format (Literal['pcm16', 'g711_ulaw', 'g711_alaw'] | None)

• tools (List[Dict] | None)

• tool_choice (Literal['auto', 'none', 'required'] | None)

• temperature (float | None)

• max_response_output_tokens (int | Literal['inf'] | None)

modalities: List[Literal['text', 'audio']] | None

instructions: str | None

voice: str | None

output_audio_format: Literal['pcm16', 'g711_ulaw', 'g711_alaw'] | None

tools: List[Dict] | None

tool_choice: Literal['auto', 'none', 'required'] | None

temperature: float | None

max_response_output_tokens: int | Literal['inf'] | None

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.RealtimeError(*, type, code='', message, param=None, event_id=None)

Bases: BaseModel

Parameters:

• type (str)

• code (str | None)

• message (str)

• param (str | None)

• event_id (str | None)

type: str

code: str | None

message: str

param: str | None

event_id: str | None

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ClientEvent(*, event_id=<factory>)

Bases: BaseModel

Parameters:

event_id (str)

event_id: str

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.SessionUpdateEvent(*, event_id=<factory>, type='session.update', session)

Bases: ClientEvent

Parameters:

• event_id (str)

• type (Literal['session.update'])

• session (SessionProperties)

type: Literal['session.update']

session: SessionProperties

model_dump(*args, **kwargs)

Usage docs: https://docs.pydantic.dev/2.10/concepts/serialization/#modelmodel_dump

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

Parameters:

• mode – The mode in which to_python should run. If mode is ‘json’, the output will only contain JSON serializable types. If mode is ‘python’, the output may contain non-JSON-serializable Python objects.

• include – A set of fields to include in the output.

• exclude – A set of fields to exclude from the output.

• context – Additional context to pass to the serializer.

• by_alias – Whether to use the field’s alias in the dictionary key if defined.

• exclude_unset – Whether to exclude fields that have not been explicitly set.

• exclude_defaults – Whether to exclude fields that are set to their default value.

• exclude_none – Whether to exclude fields that have a value of None.

• round_trip – If True, dumped values should be valid as input for non-idempotent types such as Json[T].

• warnings – How to handle serialization errors. False/”none” ignores them, True/”warn” logs errors, “error” raises a [PydanticSerializationError][pydantic_core.PydanticSerializationError].

• serialize_as_any – Whether to serialize fields with duck-typing serialization behavior.

Returns:

A dictionary representation of the model.

Return type:

Dict[str, Any]

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.InputAudioBufferAppendEvent(*, event_id=<factory>, type='input_audio_buffer.append', audio)

Bases: ClientEvent

Parameters:

• event_id (str)

• type (Literal['input_audio_buffer.append'])

• audio (str)

type: Literal['input_audio_buffer.append']

audio: str

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.InputAudioBufferCommitEvent(*, event_id=<factory>, type='input_audio_buffer.commit')

Bases: ClientEvent

Parameters:

• event_id (str)

• type (Literal['input_audio_buffer.commit'])

type: Literal['input_audio_buffer.commit']

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.InputAudioBufferClearEvent(*, event_id=<factory>, type='input_audio_buffer.clear')

Bases: ClientEvent

Parameters:

• event_id (str)

• type (Literal['input_audio_buffer.clear'])

type: Literal['input_audio_buffer.clear']

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ConversationItemCreateEvent(*, event_id=<factory>, type='conversation.item.create', previous_item_id=None, item)

Bases: ClientEvent

Parameters:

• event_id (str)

• type (Literal['conversation.item.create'])

• previous_item_id (str | None)

• item (ConversationItem)

type: Literal['conversation.item.create']

previous_item_id: str | None

item: ConversationItem

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ConversationItemTruncateEvent(*, event_id=<factory>, type='conversation.item.truncate', item_id, content_index, audio_end_ms)

Bases: ClientEvent

Parameters:

• event_id (str)

• type (Literal['conversation.item.truncate'])

• item_id (str)

• content_index (int)

• audio_end_ms (int)

type: Literal['conversation.item.truncate']

item_id: str

content_index: int

audio_end_ms: int

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ConversationItemDeleteEvent(*, event_id=<factory>, type='conversation.item.delete', item_id)

Bases: ClientEvent

Parameters:

• event_id (str)

• type (Literal['conversation.item.delete'])

• item_id (str)

type: Literal['conversation.item.delete']

item_id: str

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ConversationItemRetrieveEvent(*, event_id=<factory>, type='conversation.item.retrieve', item_id)

Bases: ClientEvent

Parameters:

• event_id (str)

• type (Literal['conversation.item.retrieve'])

• item_id (str)

type: Literal['conversation.item.retrieve']

item_id: str

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseCreateEvent(*, event_id=<factory>, type='response.create', response=None)

Bases: ClientEvent

Parameters:

• event_id (str)

• type (Literal['response.create'])

• response (ResponseProperties | None)

type: Literal['response.create']

response: ResponseProperties | None

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseCancelEvent(*, event_id=<factory>, type='response.cancel')

Bases: ClientEvent

Parameters:

• event_id (str)

• type (Literal['response.cancel'])

type: Literal['response.cancel']

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ServerEvent(*, event_id, type)

Bases: BaseModel

Parameters:

• event_id (str)

• type (str)

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

event_id: str

type: str

class pipecat.services.openai_realtime_beta.events.SessionCreatedEvent(*, event_id, type, session)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['session.created'])

• session (SessionProperties)

type: Literal['session.created']

session: SessionProperties

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.SessionUpdatedEvent(*, event_id, type, session)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['session.updated'])

• session (SessionProperties)

type: Literal['session.updated']

session: SessionProperties

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ConversationCreated(*, event_id, type, conversation)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['conversation.created'])

• conversation (RealtimeConversation)

type: Literal['conversation.created']

conversation: RealtimeConversation

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ConversationItemCreated(*, event_id, type, previous_item_id=None, item)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['conversation.item.created'])

• previous_item_id (str | None)

• item (ConversationItem)

type: Literal['conversation.item.created']

previous_item_id: str | None

item: ConversationItem

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ConversationItemInputAudioTranscriptionDelta(*, event_id, type, item_id, content_index, delta)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['conversation.item.input_audio_transcription.delta'])

• item_id (str)

• content_index (int)

• delta (str)

type: Literal['conversation.item.input_audio_transcription.delta']

item_id: str

content_index: int

delta: str

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ConversationItemInputAudioTranscriptionCompleted(*, event_id, type, item_id, content_index, transcript)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['conversation.item.input_audio_transcription.completed'])

• item_id (str)

• content_index (int)

• transcript (str)

type: Literal['conversation.item.input_audio_transcription.completed']

item_id: str

content_index: int

transcript: str

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ConversationItemInputAudioTranscriptionFailed(*, event_id, type, item_id, content_index, error)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['conversation.item.input_audio_transcription.failed'])

• item_id (str)

• content_index (int)

• error (RealtimeError)

type: Literal['conversation.item.input_audio_transcription.failed']

item_id: str

content_index: int

error: RealtimeError

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ConversationItemTruncated(*, event_id, type, item_id, content_index, audio_end_ms)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['conversation.item.truncated'])

• item_id (str)

• content_index (int)

• audio_end_ms (int)

type: Literal['conversation.item.truncated']

item_id: str

content_index: int

audio_end_ms: int

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ConversationItemDeleted(*, event_id, type, item_id)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['conversation.item.deleted'])

• item_id (str)

type: Literal['conversation.item.deleted']

item_id: str

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ConversationItemRetrieved(*, event_id, type, item)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['conversation.item.retrieved'])

• item (ConversationItem)

type: Literal['conversation.item.retrieved']

item: ConversationItem

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseCreated(*, event_id, type)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (str)

type: Literal['response.created']

response: Response

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseDone(*, event_id, type)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (str)

type: Literal['response.done']

response: Response

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseOutputItemAdded(*, event_id, type, response_id, output_index, item)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['response.output_item.added'])

• response_id (str)

• output_index (int)

• item (ConversationItem)

type: Literal['response.output_item.added']

response_id: str

output_index: int

item: ConversationItem

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseOutputItemDone(*, event_id, type, response_id, output_index, item)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['response.output_item.done'])

• response_id (str)

• output_index (int)

• item (ConversationItem)

type: Literal['response.output_item.done']

response_id: str

output_index: int

item: ConversationItem

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseContentPartAdded(*, event_id, type, response_id, item_id, output_index, content_index, part)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['response.content_part.added'])

• response_id (str)

• item_id (str)

• output_index (int)

• content_index (int)

• part (ItemContent)

type: Literal['response.content_part.added']

response_id: str

item_id: str

output_index: int

content_index: int

part: ItemContent

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseContentPartDone(*, event_id, type, response_id, item_id, output_index, content_index, part)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['response.content_part.done'])

• response_id (str)

• item_id (str)

• output_index (int)

• content_index (int)

• part (ItemContent)

type: Literal['response.content_part.done']

response_id: str

item_id: str

output_index: int

content_index: int

part: ItemContent

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseTextDelta(*, event_id, type, response_id, item_id, output_index, content_index, delta)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['response.text.delta'])

• response_id (str)

• item_id (str)

• output_index (int)

• content_index (int)

• delta (str)

type: Literal['response.text.delta']

response_id: str

item_id: str

output_index: int

content_index: int

delta: str

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseTextDone(*, event_id, type, response_id, item_id, output_index, content_index, text)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['response.text.done'])

• response_id (str)

• item_id (str)

• output_index (int)

• content_index (int)

• text (str)

type: Literal['response.text.done']

response_id: str

item_id: str

output_index: int

content_index: int

text: str

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseAudioTranscriptDelta(*, event_id, type, response_id, item_id, output_index, content_index, delta)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['response.audio_transcript.delta'])

• response_id (str)

• item_id (str)

• output_index (int)

• content_index (int)

• delta (str)

type: Literal['response.audio_transcript.delta']

response_id: str

item_id: str

output_index: int

content_index: int

delta: str

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseAudioTranscriptDone(*, event_id, type, response_id, item_id, output_index, content_index, transcript)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['response.audio_transcript.done'])

• response_id (str)

• item_id (str)

• output_index (int)

• content_index (int)

• transcript (str)

type: Literal['response.audio_transcript.done']

response_id: str

item_id: str

output_index: int

content_index: int

transcript: str

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseAudioDelta(*, event_id, type, response_id, item_id, output_index, content_index, delta)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['response.audio.delta'])

• response_id (str)

• item_id (str)

• output_index (int)

• content_index (int)

• delta (str)

type: Literal['response.audio.delta']

response_id: str

item_id: str

output_index: int

content_index: int

delta: str

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseAudioDone(*, event_id, type, response_id, item_id, output_index, content_index)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['response.audio.done'])

• response_id (str)

• item_id (str)

• output_index (int)

• content_index (int)

type: Literal['response.audio.done']

response_id: str

item_id: str

output_index: int

content_index: int

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseFunctionCallArgumentsDelta(*, event_id, type, response_id, item_id, output_index, call_id, delta)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['response.function_call_arguments.delta'])

• response_id (str)

• item_id (str)

• output_index (int)

• call_id (str)

• delta (str)

type: Literal['response.function_call_arguments.delta']

response_id: str

item_id: str

output_index: int

call_id: str

delta: str

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ResponseFunctionCallArgumentsDone(*, event_id, type, response_id, item_id, output_index, call_id, arguments)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['response.function_call_arguments.done'])

• response_id (str)

• item_id (str)

• output_index (int)

• call_id (str)

• arguments (str)

type: Literal['response.function_call_arguments.done']

response_id: str

item_id: str

output_index: int

call_id: str

arguments: str

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.InputAudioBufferSpeechStarted(*, event_id, type, audio_start_ms, item_id)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['input_audio_buffer.speech_started'])

• audio_start_ms (int)

• item_id (str)

type: Literal['input_audio_buffer.speech_started']

audio_start_ms: int

item_id: str

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.InputAudioBufferSpeechStopped(*, event_id, type, audio_end_ms, item_id)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['input_audio_buffer.speech_stopped'])

• audio_end_ms (int)

• item_id (str)

type: Literal['input_audio_buffer.speech_stopped']

audio_end_ms: int

item_id: str

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.InputAudioBufferCommitted(*, event_id, type, previous_item_id=None, item_id)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['input_audio_buffer.committed'])

• previous_item_id (str | None)

• item_id (str)

type: Literal['input_audio_buffer.committed']

previous_item_id: str | None

item_id: str

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.InputAudioBufferCleared(*, event_id, type)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['input_audio_buffer.cleared'])

type: Literal['input_audio_buffer.cleared']

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.ErrorEvent(*, event_id, type, error)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['error'])

• error (RealtimeError)

type: Literal['error']

error: RealtimeError

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.RateLimitsUpdated(*, event_id, type, rate_limits)

Bases: ServerEvent

Parameters:

• event_id (str)

• type (Literal['rate_limits.updated'])

• rate_limits (List[Dict[str, Any]])

type: Literal['rate_limits.updated']

rate_limits: List[Dict[str, Any]]

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.TokenDetails(*, cached_tokens=0, text_tokens=0, audio_tokens=0, **extra_data)

Bases: BaseModel

Parameters:

• cached_tokens (int | None)

• text_tokens (int | None)

• audio_tokens (int | None)

• extra_data (Any)

cached_tokens: int | None

text_tokens: int | None

audio_tokens: int | None

class Config

Bases: object

extra = 'allow'

model_config: ClassVar[ConfigDict] = {'extra': 'allow'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.Usage(*, total_tokens, input_tokens, output_tokens, input_token_details, output_token_details)

Bases: BaseModel

Parameters:

• total_tokens (int)

• input_tokens (int)

• output_tokens (int)

• input_token_details (TokenDetails)

• output_token_details (TokenDetails)

total_tokens: int

input_tokens: int

output_tokens: int

input_token_details: TokenDetails

output_token_details: TokenDetails

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class pipecat.services.openai_realtime_beta.events.Response(*, id, object, status, status_details, output, usage=None)

Bases: BaseModel

Parameters:

• id (str)

• object (Literal['realtime.response'])

• status (Literal['completed', 'in_progress', 'incomplete', 'cancelled', 'failed'])

• status_details (Any)

• output (List[ConversationItem])

• usage (Usage | None)

id: str

object: Literal['realtime.response']

status: Literal['completed', 'in_progress', 'incomplete', 'cancelled', 'failed']

status_details: Any

output: List[ConversationItem]

usage: Usage | None

model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

pipecat.services.openai_realtime_beta.events.parse_server_event(str)