OpenAI API

RealtimeClientEventResponseCreate

object

This event instructs the server to create a Response, which means triggering
model inference. When in Server VAD mode, the server will create Responses
automatically.

A Response will include at least one Item, and may have two, in which case
the second will be a function call. These Items will be appended to the
conversation history.

The server will respond with a response.created event, events for Items
and content created, and finally a response.done event to indicate the
Response is complete.

The response.create event includes inference configuration like
instructions, and temperature. These fields will override the Session’s
configuration for this Response only.

event_idstring

Optional client-generated ID used to identify this event.

typestringrequired

The event type, must be response.create.

Allowed values:response.create

responseobject

Create a new Realtime response with these parameters

Show Child Parameters
Example

RealtimeClientEventSessionUpdate

object

Send this event to update the session’s default configuration. The client may
send this event at any time to update the session configuration, and any
field may be updated at any time, except for “voice”. The server will respond
with a session.updated event that shows the full effective configuration.
Only fields that are present are updated, thus the correct way to clear a
field like “instructions” is to pass an empty string.

event_idstring

Optional client-generated ID used to identify this event.

typestringrequired

The event type, must be session.update.

Allowed values:session.update

sessionobjectrequired

Realtime session object configuration.

Show Child Parameters
Example

RealtimeConversationItem

object

The item to add to the conversation.

idstring

The unique ID of the item, this can be generated by the client to help
manage server-side context, but is not required because the server will
generate one if not provided.

typestring

The type of the item (message, function_call, function_call_output).

Allowed values:messagefunction_callfunction_call_output

objectstring

Identifier for the API object being returned - always realtime.item.

Allowed values:realtime.item

statusstring

The status of the item (completed, incomplete). These have no effect
on the conversation, but are accepted for consistency with the
conversation.item.created event.

Allowed values:completedincomplete

rolestring

The role of the message sender (user, assistant, system), only
applicable for message items.

Allowed values:userassistantsystem

contentarray[object]

The content of the message, applicable for message items.

  • Message items of role system support only input_text content
  • Message items of role user support input_text and input_audio
    content
  • Message items of role assistant support text content.
Show Child Parameters
call_idstring

The ID of the function call (for function_call and
function_call_output items). If passed on a function_call_output
item, the server will check that a function_call item with the same
ID exists in the conversation history.

namestring

The name of the function being called (for function_call items).

argumentsstring

The arguments of the function call (for function_call items).

outputstring

The output of the function call (for function_call_output items).

Example

RealtimeConversationItemWithReference

object

The item to add to the conversation.

idstring

For an item of type (message | function_call | function_call_output)
this field allows the client to assign the unique ID of the item. It is
not required because the server will generate one if not provided.

For an item of type item_reference, this field is required and is a
reference to any item that has previously existed in the conversation.

typestring

The type of the item (message, function_call, function_call_output, item_reference).

Allowed values:messagefunction_callfunction_call_output

objectstring

Identifier for the API object being returned - always realtime.item.

Allowed values:realtime.item

statusstring

The status of the item (completed, incomplete). These have no effect
on the conversation, but are accepted for consistency with the
conversation.item.created event.

Allowed values:completedincomplete

rolestring

The role of the message sender (user, assistant, system), only
applicable for message items.

Allowed values:userassistantsystem

contentarray[object]

The content of the message, applicable for message items.

  • Message items of role system support only input_text content
  • Message items of role user support input_text and input_audio
    content
  • Message items of role assistant support text content.
Show Child Parameters
call_idstring

The ID of the function call (for function_call and
function_call_output items). If passed on a function_call_output
item, the server will check that a function_call item with the same
ID exists in the conversation history.

namestring

The name of the function being called (for function_call items).

argumentsstring

The arguments of the function call (for function_call items).

outputstring

The output of the function call (for function_call_output items).

Example

RealtimeResponse

object

The response resource.

idstring

The unique ID of the response.

objectstring

The object type, must be realtime.response.

Allowed values:realtime.response

statusstring

The final status of the response (completed, cancelled, failed, or
incomplete).

Allowed values:completedcancelledfailedincomplete

status_detailsobject

Additional details about the status.

Show Child Parameters
outputarray[object]

The item to add to the conversation.

Show Child Parameters
metadataobject

Set of 16 key-value pairs that can be attached to an object. This can be
useful for storing additional information about the object in a structured
format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings
with a maximum length of 512 characters.

usageobject

Usage statistics for the Response, this will correspond to billing. A
Realtime API session will maintain a conversation context and append new
Items to the Conversation, thus output from previous turns (text and
audio tokens) will become the input for later turns.

Show Child Parameters
conversation_idstring

Which conversation the response is added to, determined by the conversation
field in the response.create event. If auto, the response will be added to
the default conversation and the value of conversation_id will be an id like
conv_1234. If none, the response will not be added to any conversation and
the value of conversation_id will be null. If responses are being triggered
by server VAD, the response will be added to the default conversation, thus
the conversation_id will be an id like conv_1234.

voicestring

The voice the model used to respond.
Current voice options are alloy, ash, ballad, coral, echo sage,
shimmer and verse.

Allowed values:alloyashballadcoralechosageshimmerverse

modalitiesarray[string]

The set of modalities the model used to respond. If there are multiple modalities,
the model will pick one, for example if modalities is ["text", "audio"], the model
could be responding in either text or audio.

Allowed values:textaudio

output_audio_formatstring

The format of output audio. Options are pcm16, g711_ulaw, or g711_alaw.

Allowed values:pcm16g711_ulawg711_alaw

temperaturenumber

Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8.

max_output_tokensOne Of

Maximum number of output tokens for a single assistant response,
inclusive of tool calls, that was used in this response.

Variant 1integer
Example