OpenAIRealtimeSIP

Transport layer that connects to an existing SIP-initiated Realtime call via call ID.

Extends

OpenAIRealtimeWebSocket

Constructors

Constructor

new OpenAIRealtimeSIP(options): OpenAIRealtimeSIP;

Parameters

Parameter	Type
`options`	`OpenAIRealtimeWebSocketOptions`

Returns

OpenAIRealtimeSIP

Overrides

OpenAIRealtimeWebSocket.constructor

Accessors

_tracingConfig

Set Signature

set _tracingConfig(tracingConfig): void;

Sets the internal tracing config. This is used to track the tracing config that has been set during the session.create event.

Parameters

Parameter	Type
`tracingConfig`	`RealtimeTracingConfig` \| `null`

Returns

void

Inherited from

OpenAIRealtimeWebSocket._tracingConfig

connectionState

Get Signature

get connectionState(): WebSocketState;

The current connection state of the WebSocket connection.

Returns

WebSocketState

Inherited from

OpenAIRealtimeWebSocket.connectionState

currentModel

Get Signature

get currentModel(): OpenAIRealtimeModels;

The current model that is being used by the transport layer.

Returns

OpenAIRealtimeModels

Set Signature

set currentModel(model): void;

The current model that is being used by the transport layer. Note: The model cannot be changed mid conversation.

Parameters

Parameter	Type
`model`	`OpenAIRealtimeModels`

Returns

void

Inherited from

OpenAIRealtimeWebSocket.currentModel

muted

Get Signature

get muted(): null;

Always returns null as the WebSocket transport layer does not handle muting. Instead, this should be handled by the client by not triggering the sendAudio method.

Returns

null

Whether the input audio track is currently muted null if the muting is not handled by the transport layer

Inherited from

OpenAIRealtimeWebSocket.muted

status

Get Signature

get status(): "connecting" | "connected" | "disconnected";

The current status of the WebSocket connection.

Returns

"connecting" | "connected" | "disconnected"

Inherited from

OpenAIRealtimeWebSocket.status

Methods

_cancelResponse()

_cancelResponse(): void;

Send a cancel response event to the Realtime API. This is used to cancel an ongoing response that the model is currently generating.

Returns

void

Inherited from

OpenAIRealtimeWebSocket._cancelResponse

_interrupt()

_interrupt(elapsedTime, cancelOngoingResponse): void;

Do NOT call this method directly. Call interrupt() instead for proper interruption handling.

This method is used to send the right events to the API to inform the model that the user has interrupted the response. It might be overridden/extended by an extended transport layer. See the TwilioRealtimeTransportLayer for an example.

Parameters

Parameter	Type	Default value	Description
`elapsedTime`	`number`	`undefined`	The elapsed time since the response started.
`cancelOngoingResponse`	`boolean`	`true`	‐

Returns

void

Inherited from

OpenAIRealtimeWebSocket._interrupt

addImage()

addImage(image, options): void;

Sends an image to the model

Parameters

Parameter	Type	Description
`image`	`string`	The image to send
`options`	{ `triggerResponse?`: `boolean`; }	Additional options
`options.triggerResponse?`	`boolean`	Whether to trigger a response from the model

Returns

void

Inherited from

OpenAIRealtimeWebSocket.addImage

buildSessionPayload()

buildSessionPayload(config): RealtimeSessionPayload;

Build the payload object expected by the Realtime API when creating or updating a session.

The helper centralises the conversion from camelCase runtime config to the snake_case payload required by the Realtime API so transports that need a one-off payload (for example SIP call acceptance) can reuse the same logic without duplicating private state.

Parameters

Parameter	Type	Description
`config`	`Partial`<`RealtimeSessionConfig`>	The session config to merge with defaults.

Returns

RealtimeSessionPayload

Inherited from

OpenAIRealtimeWebSocket.buildSessionPayload

close()

close(): void;

Close the WebSocket connection.

This will also reset any internal connection tracking used for interruption handling.

Returns

void

Inherited from

OpenAIRealtimeWebSocket.close

connect()

connect(options): Promise<void>;

Establishes the connection to the model and keeps the connection alive

Parameters

Parameter	Type	Description
`options`	`RealtimeTransportLayerConnectOptions`	The options for the connection

Returns

Promise<void>

Overrides

OpenAIRealtimeWebSocket.connect

emit()

emit<K>(type, ...args): boolean;

Type Parameters

Type Parameter
`K` extends keyof `RealtimeTransportEventTypes`

Parameters

Parameter	Type
`type`	`K`
…`args`	`OpenAIRealtimeEventTypes`[`K`]

Returns

boolean

Inherited from

OpenAIRealtimeWebSocket.emit

interrupt()

interrupt(cancelOngoingResponse): void;

Interrupt the ongoing response. This method is triggered automatically by the client when voice activity detection (VAD) is enabled (default) as well as when an output guardrail got triggered.

You can also call this method directly if you want to interrupt the conversation for example based on an event in the client.

Parameters

Parameter	Type	Default value
`cancelOngoingResponse`	`boolean`	`true`

Returns

void

Inherited from

OpenAIRealtimeWebSocket.interrupt

mute()

mute(_muted): never;

Will throw an error as the WebSocket transport layer does not support muting.

Parameters

Parameter	Type
`_muted`	`boolean`

Returns

never

Inherited from

OpenAIRealtimeWebSocket.mute

off()

off<K>(type, listener): EventEmitter<EventTypes>;

Type Parameters

Type Parameter
`K` extends keyof `RealtimeTransportEventTypes`

Parameters

Parameter	Type
`type`	`K`
`listener`	(…`args`) => `void`

Returns

EventEmitter<EventTypes>

Inherited from

OpenAIRealtimeWebSocket.off

on()

on<K>(type, listener): EventEmitter<EventTypes>;

Type Parameters

Type Parameter
`K` extends keyof `RealtimeTransportEventTypes`

Parameters

Parameter	Type
`type`	`K`
`listener`	(…`args`) => `void`

Returns

EventEmitter<EventTypes>

Inherited from

OpenAIRealtimeWebSocket.on

once()

once<K>(type, listener): EventEmitter<EventTypes>;

Type Parameters

Type Parameter
`K` extends keyof `RealtimeTransportEventTypes`

Parameters

Parameter	Type
`type`	`K`
`listener`	(…`args`) => `void`

Returns

EventEmitter<EventTypes>

Inherited from

OpenAIRealtimeWebSocket.once

resetHistory()

resetHistory(oldHistory, newHistory): void;

Reset the history of the conversation. This will create a diff between the old and new history and send the necessary events to the Realtime API to update the history.

Parameters

Parameter	Type	Description
`oldHistory`	`RealtimeItem`[]	The old history of the conversation.
`newHistory`	`RealtimeItem`[]	The new history of the conversation.

Returns

void

Inherited from

OpenAIRealtimeWebSocket.resetHistory

sendAudio()

sendAudio(_audio, _options): never;

Send an audio buffer to the Realtime API. This is used for your client to send audio to the model to respond.

Parameters

Parameter	Type
`_audio`	`ArrayBuffer`
`_options`	{ `commit?`: `boolean`; }
`_options.commit?`	`boolean`

Returns

never

Overrides

OpenAIRealtimeWebSocket.sendAudio

sendEvent()

sendEvent(event): void;

Send an event to the Realtime API. This will stringify the event and send it directly to the API. This can be used if you want to take control over the connection and send events manually.

Parameters

Parameter	Type	Description
`event`	`RealtimeClientMessage`	The event to send.

Returns

void

Inherited from

OpenAIRealtimeWebSocket.sendEvent

sendFunctionCallOutput()

sendFunctionCallOutput(
 toolCall,
 output,
 startResponse): void;

Send the output of a function call to the Realtime API.

Parameters

Parameter	Type	Default value	Description
`toolCall`	`TransportToolCallEvent`	`undefined`	The tool call to send the output for.
`output`	`string`	`undefined`	The output of the function call.
`startResponse`	`boolean`	`true`	Whether to start a new response after sending the output.

Returns

void

Inherited from

OpenAIRealtimeWebSocket.sendFunctionCallOutput

sendMcpResponse()

sendMcpResponse(approvalRequest, approved): void;

Sends a response for an MCP tool call

Parameters

Parameter	Type	Description
`approvalRequest`	{ `approved?`: `boolean` \| `null`; `arguments`: `Record`<`string`, `any`>; `itemId`: `string`; `name`: `string`; `serverLabel`: `string`; `type`: `"mcp_approval_request"`; }	The approval request to respond to
`approvalRequest.approved?`	`boolean` \| `null`	‐
`approvalRequest.arguments`	`Record`<`string`, `any`>	‐
`approvalRequest.itemId`	`string`	‐
`approvalRequest.name`	`string`	‐
`approvalRequest.serverLabel`	`string`	‐
`approvalRequest.type`	`"mcp_approval_request"`	‐
`approved`	`boolean`	Whether the tool call was approved or rejected

Returns

void

Inherited from

OpenAIRealtimeWebSocket.sendMcpResponse

sendMessage()

sendMessage(
 message,
 otherEventData,
 __namedParameters): void;

Send a message to the Realtime API. This will create a new item in the conversation and trigger a response.

Parameters

Parameter	Type	Description
`message`	`RealtimeUserInput`	The message to send.
`otherEventData`	`Record`<`string`, `any`>	Additional event data to send.
`__namedParameters`	{ `triggerResponse?`: `boolean`; }	‐
`__namedParameters.triggerResponse?`	`boolean`	‐

Returns

void

Inherited from

OpenAIRealtimeWebSocket.sendMessage

updateSessionConfig()

updateSessionConfig(config): void;

Updates the session config. This will merge it with the current session config with the default values and send it to the Realtime API.

Parameters

Parameter	Type	Description
`config`	`Partial`<`RealtimeSessionConfig`>	The session config to update.

Returns

void

Inherited from

OpenAIRealtimeWebSocket.updateSessionConfig

buildInitialConfig()

static buildInitialConfig<TBaseContext>(
 agent,
 options,
overrides): Promise<RealtimeSessionPayload>;

Build the initial session payload for a SIP-attached session, matching the config that a RealtimeSession would send on connect.

This enables SIP deployments to accept an incoming call with a payload that already reflects the active agent’s instructions, tools, prompt, and tracing metadata without duplicating the session logic outside of the SDK. The returned object structurally matches the REST CallAcceptParams interface, so it can be forwarded directly to openai.realtime.calls.accept(...).

Type Parameters

Type Parameter	Default type
`TBaseContext`	`unknown`

Parameters

Parameter	Type	Description
`agent`	\| `RealtimeAgent`<`TBaseContext`> \| `RealtimeAgent`<`RealtimeContextData`<`TBaseContext`>>	The starting agent used to seed the session instructions, tools, and prompt.
`options`	`Partial`<`RealtimeSessionOptions`<`TBaseContext`>>	Optional session options that mirror the ones passed to the RealtimeSession constructor.
`overrides`	`Partial`<`RealtimeSessionConfig`>	Additional config overrides applied on top of the session options.

Returns

Promise<RealtimeSessionPayload>