All Implemented Interfaces:


public final class RealtimeClientEvent

A realtime client event.

Nested Class Summary

Nested Classes
Modifier and Type	Class	Description
`public interface`	`RealtimeClientEvent.Visitor`	An interface that defines how to map each variant of RealtimeClientEvent to a value of type T.

Field Summary

Fields
Modifier and Type	Field	Description

Constructor Summary

Constructors
Constructor	Description

Enum Constant Summary

Enum Constants
Enum Constant	Description

Method Summary

Modifier and Type	Method	Description
`final Optional<ConversationItemCreateEvent>`	`conversationItemCreate()`	Add a new Item to the Conversation's context, including messages, function calls, and function call responses.
`final Optional<ConversationItemDeleteEvent>`	`conversationItemDelete()`	Send this event when you want to remove any item from the conversation history.
`final Optional<ConversationItemRetrieveEvent>`	`conversationItemRetrieve()`	Send this event when you want to retrieve the server's representation of a specific item in the conversation history.
`final Optional<ConversationItemTruncateEvent>`	`conversationItemTruncate()`	Send this event to truncate a previous assistant message’s audio.
`final Optional<InputAudioBufferAppendEvent>`	`inputAudioBufferAppend()`	Send this event to append audio bytes to the input audio buffer.
`final Optional<InputAudioBufferClearEvent>`	`inputAudioBufferClear()`	Send this event to clear the audio bytes in the buffer.
`final Optional<OutputAudioBufferClearEvent>`	`outputAudioBufferClear()`	WebRTC Only: Emit to cut off the current audio response.
`final Optional<InputAudioBufferCommitEvent>`	`inputAudioBufferCommit()`	Send this event to commit the user input audio buffer, which will create a new user message item in the conversation.
`final Optional<ResponseCancelEvent>`	`responseCancel()`	Send this event to cancel an in-progress response.
`final Optional<ResponseCreateEvent>`	`responseCreate()`	This event instructs the server to create a Response, which means triggering model inference.
`final Optional<SessionUpdateEvent>`	`sessionUpdate()`	Send this event to update the session’s default configuration.
`final Optional<TranscriptionSessionUpdate>`	`transcriptionSessionUpdate()`	Send this event to update a transcription session.
`final Boolean`	`isConversationItemCreate()`
`final Boolean`	`isConversationItemDelete()`
`final Boolean`	`isConversationItemRetrieve()`
`final Boolean`	`isConversationItemTruncate()`
`final Boolean`	`isInputAudioBufferAppend()`
`final Boolean`	`isInputAudioBufferClear()`
`final Boolean`	`isOutputAudioBufferClear()`
`final Boolean`	`isInputAudioBufferCommit()`
`final Boolean`	`isResponseCancel()`
`final Boolean`	`isResponseCreate()`
`final Boolean`	`isSessionUpdate()`
`final Boolean`	`isTranscriptionSessionUpdate()`
`final ConversationItemCreateEvent`	`asConversationItemCreate()`	Add a new Item to the Conversation's context, including messages, function calls, and function call responses.
`final ConversationItemDeleteEvent`	`asConversationItemDelete()`	Send this event when you want to remove any item from the conversation history.
`final ConversationItemRetrieveEvent`	`asConversationItemRetrieve()`	Send this event when you want to retrieve the server's representation of a specific item in the conversation history.
`final ConversationItemTruncateEvent`	`asConversationItemTruncate()`	Send this event to truncate a previous assistant message’s audio.
`final InputAudioBufferAppendEvent`	`asInputAudioBufferAppend()`	Send this event to append audio bytes to the input audio buffer.
`final InputAudioBufferClearEvent`	`asInputAudioBufferClear()`	Send this event to clear the audio bytes in the buffer.
`final OutputAudioBufferClearEvent`	`asOutputAudioBufferClear()`	WebRTC Only: Emit to cut off the current audio response.
`final InputAudioBufferCommitEvent`	`asInputAudioBufferCommit()`	Send this event to commit the user input audio buffer, which will create a new user message item in the conversation.
`final ResponseCancelEvent`	`asResponseCancel()`	Send this event to cancel an in-progress response.
`final ResponseCreateEvent`	`asResponseCreate()`	This event instructs the server to create a Response, which means triggering model inference.
`final SessionUpdateEvent`	`asSessionUpdate()`	Send this event to update the session’s default configuration.
`final TranscriptionSessionUpdate`	`asTranscriptionSessionUpdate()`	Send this event to update a transcription session.
`final Optional<JsonValue>`	`_json()`
`final <T extends Any> T`	`accept(RealtimeClientEvent.Visitor<T> visitor)`
`final RealtimeClientEvent`	`validate()`
`final Boolean`	`isValid()`
`Boolean`	`equals(Object other)`
`Integer`	`hashCode()`
`String`	`toString()`
`final static RealtimeClientEvent`	`ofConversationItemCreate(ConversationItemCreateEvent conversationItemCreate)`	Add a new Item to the Conversation's context, including messages, function calls, and function call responses.
`final static RealtimeClientEvent`	`ofConversationItemDelete(ConversationItemDeleteEvent conversationItemDelete)`	Send this event when you want to remove any item from the conversation history.
`final static RealtimeClientEvent`	`ofConversationItemRetrieve(ConversationItemRetrieveEvent conversationItemRetrieve)`	Send this event when you want to retrieve the server's representation of a specific item in the conversation history.
`final static RealtimeClientEvent`	`ofConversationItemTruncate(ConversationItemTruncateEvent conversationItemTruncate)`	Send this event to truncate a previous assistant message’s audio.
`final static RealtimeClientEvent`	`ofInputAudioBufferAppend(InputAudioBufferAppendEvent inputAudioBufferAppend)`	Send this event to append audio bytes to the input audio buffer.
`final static RealtimeClientEvent`	`ofInputAudioBufferClear(InputAudioBufferClearEvent inputAudioBufferClear)`	Send this event to clear the audio bytes in the buffer.
`final static RealtimeClientEvent`	`ofOutputAudioBufferClear(OutputAudioBufferClearEvent outputAudioBufferClear)`	WebRTC Only: Emit to cut off the current audio response.
`final static RealtimeClientEvent`	`ofInputAudioBufferCommit(InputAudioBufferCommitEvent inputAudioBufferCommit)`	Send this event to commit the user input audio buffer, which will create a new user message item in the conversation.
`final static RealtimeClientEvent`	`ofResponseCancel(ResponseCancelEvent responseCancel)`	Send this event to cancel an in-progress response.
`final static RealtimeClientEvent`	`ofResponseCreate(ResponseCreateEvent responseCreate)`	This event instructs the server to create a Response, which means triggering model inference.
`final static RealtimeClientEvent`	`ofSessionUpdate(SessionUpdateEvent sessionUpdate)`	Send this event to update the session’s default configuration.
`final static RealtimeClientEvent`	`ofTranscriptionSessionUpdate(TranscriptionSessionUpdate transcriptionSessionUpdate)`	Send this event to update a transcription session.

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
- Method Detail
  - conversationItemCreate
```
 final Optional<ConversationItemCreateEvent> conversationItemCreate()
```
    Add a new Item to the Conversation's context, including messages, function calls, and function call responses. This event can be used both to populate a "history" of the conversation and to add new items mid-stream, but has the current limitation that it cannot populate assistant audio messages.
    If successful, the server will respond with a conversation.item.created event, otherwise an error event will be sent.
  - conversationItemDelete
```
 final Optional<ConversationItemDeleteEvent> conversationItemDelete()
```
    Send this event when you want to remove any item from the conversation history. The server will respond with a conversation.item.deleted event, unless the item does not exist in the conversation history, in which case the server will respond with an error.
  - conversationItemRetrieve
```
 final Optional<ConversationItemRetrieveEvent> conversationItemRetrieve()
```
    Send this event when you want to retrieve the server's representation of a specific item in the conversation history. This is useful, for example, to inspect user audio after noise cancellation and VAD. The server will respond with a conversation.item.retrieved event, unless the item does not exist in the conversation history, in which case the server will respond with an error.
  - conversationItemTruncate
```
 final Optional<ConversationItemTruncateEvent> conversationItemTruncate()
```
    Send this event to truncate a previous assistant message’s audio. The server will produce audio faster than realtime, so this event is useful when the user interrupts to truncate audio that has already been sent to the client but not yet played. This will synchronize the server's understanding of the audio with the client's playback.
    Truncating audio will delete the server-side text transcript to ensure there is not text in the context that hasn't been heard by the user.
    If successful, the server will respond with a conversation.item.truncated event.
  - inputAudioBufferAppend
```
 final Optional<InputAudioBufferAppendEvent> inputAudioBufferAppend()
```
    Send this event to append audio bytes to the input audio buffer. The audio buffer is temporary storage you can write to and later commit. In Server VAD mode, the audio buffer is used to detect speech and the server will decide when to commit. When Server VAD is disabled, you must commit the audio buffer manually.
    The client may choose how much audio to place in each event up to a maximum of 15 MiB, for example streaming smaller chunks from the client may allow the VAD to be more responsive. Unlike made other client events, the server will not send a confirmation response to this event.
  - inputAudioBufferClear
```
 final Optional<InputAudioBufferClearEvent> inputAudioBufferClear()
```
    Send this event to clear the audio bytes in the buffer. The server will respond with an input_audio_buffer.cleared event.
  - outputAudioBufferClear
```
 final Optional<OutputAudioBufferClearEvent> outputAudioBufferClear()
```
    WebRTC Only: Emit to cut off the current audio response. This will trigger the server to stop generating audio and emit a output_audio_buffer.cleared event. This event should be preceded by a response.cancel client event to stop the generation of the current response. Learn more.
  - inputAudioBufferCommit
```
 final Optional<InputAudioBufferCommitEvent> inputAudioBufferCommit()
```
    Send this event to commit the user input audio buffer, which will create a new user message item in the conversation. This event will produce an error if the input audio buffer is empty. When in Server VAD mode, the client does not need to send this event, the server will commit the audio buffer automatically.
    Committing the input audio buffer will trigger input audio transcription (if enabled in session configuration), but it will not create a response from the model. The server will respond with an input_audio_buffer.committed event.
  - responseCancel
```
 final Optional<ResponseCancelEvent> responseCancel()
```
    Send this event to cancel an in-progress response. The server will respond with a response.done event with a status of response.status=cancelled. If there is no response to cancel, the server will respond with an error.
  - responseCreate
```
 final Optional<ResponseCreateEvent> responseCreate()
```
    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.
  - sessionUpdate
```
 final Optional<SessionUpdateEvent> sessionUpdate()
```
    Send this event to update the session’s default configuration. The client may send this event at any time to update any field, except for voice. However, note that once a session has been initialized with a particular model, it can’t be changed to another model using session.update.
    When the server receives a session.update, it will respond with a session.updated event showing the full, effective configuration. Only the fields that are present are updated. To clear a field like instructions, pass an empty string.
  - transcriptionSessionUpdate
```
 final Optional<TranscriptionSessionUpdate> transcriptionSessionUpdate()
```
    Send this event to update a transcription session.
  - isConversationItemCreate
```
 final Boolean isConversationItemCreate()
```
  - isConversationItemDelete
```
 final Boolean isConversationItemDelete()
```
  - isConversationItemRetrieve
```
 final Boolean isConversationItemRetrieve()
```
  - isConversationItemTruncate
```
 final Boolean isConversationItemTruncate()
```
  - isInputAudioBufferAppend
```
 final Boolean isInputAudioBufferAppend()
```
  - isInputAudioBufferClear
```
 final Boolean isInputAudioBufferClear()
```
  - isOutputAudioBufferClear
```
 final Boolean isOutputAudioBufferClear()
```
  - isInputAudioBufferCommit
```
 final Boolean isInputAudioBufferCommit()
```
  - isResponseCancel
```
 final Boolean isResponseCancel()
```
  - isResponseCreate
```
 final Boolean isResponseCreate()
```
  - isSessionUpdate
```
 final Boolean isSessionUpdate()
```
  - isTranscriptionSessionUpdate
```
 final Boolean isTranscriptionSessionUpdate()
```
  - asConversationItemCreate
```
 final ConversationItemCreateEvent asConversationItemCreate()
```
    Add a new Item to the Conversation's context, including messages, function calls, and function call responses. This event can be used both to populate a "history" of the conversation and to add new items mid-stream, but has the current limitation that it cannot populate assistant audio messages.
    If successful, the server will respond with a conversation.item.created event, otherwise an error event will be sent.
  - asConversationItemDelete
```
 final ConversationItemDeleteEvent asConversationItemDelete()
```
    Send this event when you want to remove any item from the conversation history. The server will respond with a conversation.item.deleted event, unless the item does not exist in the conversation history, in which case the server will respond with an error.
  - asConversationItemRetrieve
```
 final ConversationItemRetrieveEvent asConversationItemRetrieve()
```
    Send this event when you want to retrieve the server's representation of a specific item in the conversation history. This is useful, for example, to inspect user audio after noise cancellation and VAD. The server will respond with a conversation.item.retrieved event, unless the item does not exist in the conversation history, in which case the server will respond with an error.
  - asConversationItemTruncate
```
 final ConversationItemTruncateEvent asConversationItemTruncate()
```
    Send this event to truncate a previous assistant message’s audio. The server will produce audio faster than realtime, so this event is useful when the user interrupts to truncate audio that has already been sent to the client but not yet played. This will synchronize the server's understanding of the audio with the client's playback.
    Truncating audio will delete the server-side text transcript to ensure there is not text in the context that hasn't been heard by the user.
    If successful, the server will respond with a conversation.item.truncated event.
  - asInputAudioBufferAppend
```
 final InputAudioBufferAppendEvent asInputAudioBufferAppend()
```
    Send this event to append audio bytes to the input audio buffer. The audio buffer is temporary storage you can write to and later commit. In Server VAD mode, the audio buffer is used to detect speech and the server will decide when to commit. When Server VAD is disabled, you must commit the audio buffer manually.
    The client may choose how much audio to place in each event up to a maximum of 15 MiB, for example streaming smaller chunks from the client may allow the VAD to be more responsive. Unlike made other client events, the server will not send a confirmation response to this event.
  - asInputAudioBufferClear
```
 final InputAudioBufferClearEvent asInputAudioBufferClear()
```
    Send this event to clear the audio bytes in the buffer. The server will respond with an input_audio_buffer.cleared event.
  - asOutputAudioBufferClear
```
 final OutputAudioBufferClearEvent asOutputAudioBufferClear()
```
    WebRTC Only: Emit to cut off the current audio response. This will trigger the server to stop generating audio and emit a output_audio_buffer.cleared event. This event should be preceded by a response.cancel client event to stop the generation of the current response. Learn more.
  - asInputAudioBufferCommit
```
 final InputAudioBufferCommitEvent asInputAudioBufferCommit()
```
    Send this event to commit the user input audio buffer, which will create a new user message item in the conversation. This event will produce an error if the input audio buffer is empty. When in Server VAD mode, the client does not need to send this event, the server will commit the audio buffer automatically.
    Committing the input audio buffer will trigger input audio transcription (if enabled in session configuration), but it will not create a response from the model. The server will respond with an input_audio_buffer.committed event.
  - asResponseCancel
```
 final ResponseCancelEvent asResponseCancel()
```
    Send this event to cancel an in-progress response. The server will respond with a response.done event with a status of response.status=cancelled. If there is no response to cancel, the server will respond with an error.
  - asResponseCreate
```
 final ResponseCreateEvent asResponseCreate()
```
    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.
  - asSessionUpdate
```
 final SessionUpdateEvent asSessionUpdate()
```
    Send this event to update the session’s default configuration. The client may send this event at any time to update any field, except for voice. However, note that once a session has been initialized with a particular model, it can’t be changed to another model using session.update.
    When the server receives a session.update, it will respond with a session.updated event showing the full, effective configuration. Only the fields that are present are updated. To clear a field like instructions, pass an empty string.
  - asTranscriptionSessionUpdate
```
 final TranscriptionSessionUpdate asTranscriptionSessionUpdate()
```
    Send this event to update a transcription session.
  - _json
```
 final Optional<JsonValue> _json()
```
  - accept
```
 final <T extends Any> T accept(RealtimeClientEvent.Visitor<T> visitor)
```
  - validate
```
 final RealtimeClientEvent validate()
```
  - isValid
```
 final Boolean isValid()
```
  - equals
```
 Boolean equals(Object other)
```
  - hashCode
```
 Integer hashCode()
```
  - toString
```
 String toString()
```
  - ofConversationItemCreate
```
 final static RealtimeClientEvent ofConversationItemCreate(ConversationItemCreateEvent conversationItemCreate)
```
    Add a new Item to the Conversation's context, including messages, function calls, and function call responses. This event can be used both to populate a "history" of the conversation and to add new items mid-stream, but has the current limitation that it cannot populate assistant audio messages.
    If successful, the server will respond with a conversation.item.created event, otherwise an error event will be sent.
  - ofConversationItemDelete
```
 final static RealtimeClientEvent ofConversationItemDelete(ConversationItemDeleteEvent conversationItemDelete)
```
    Send this event when you want to remove any item from the conversation history. The server will respond with a conversation.item.deleted event, unless the item does not exist in the conversation history, in which case the server will respond with an error.
  - ofConversationItemRetrieve
```
 final static RealtimeClientEvent ofConversationItemRetrieve(ConversationItemRetrieveEvent conversationItemRetrieve)
```
    Send this event when you want to retrieve the server's representation of a specific item in the conversation history. This is useful, for example, to inspect user audio after noise cancellation and VAD. The server will respond with a conversation.item.retrieved event, unless the item does not exist in the conversation history, in which case the server will respond with an error.
  - ofConversationItemTruncate
```
 final static RealtimeClientEvent ofConversationItemTruncate(ConversationItemTruncateEvent conversationItemTruncate)
```
    Send this event to truncate a previous assistant message’s audio. The server will produce audio faster than realtime, so this event is useful when the user interrupts to truncate audio that has already been sent to the client but not yet played. This will synchronize the server's understanding of the audio with the client's playback.
    Truncating audio will delete the server-side text transcript to ensure there is not text in the context that hasn't been heard by the user.
    If successful, the server will respond with a conversation.item.truncated event.
  - ofInputAudioBufferAppend
```
 final static RealtimeClientEvent ofInputAudioBufferAppend(InputAudioBufferAppendEvent inputAudioBufferAppend)
```
    Send this event to append audio bytes to the input audio buffer. The audio buffer is temporary storage you can write to and later commit. In Server VAD mode, the audio buffer is used to detect speech and the server will decide when to commit. When Server VAD is disabled, you must commit the audio buffer manually.
    The client may choose how much audio to place in each event up to a maximum of 15 MiB, for example streaming smaller chunks from the client may allow the VAD to be more responsive. Unlike made other client events, the server will not send a confirmation response to this event.
  - ofInputAudioBufferClear
```
 final static RealtimeClientEvent ofInputAudioBufferClear(InputAudioBufferClearEvent inputAudioBufferClear)
```
    Send this event to clear the audio bytes in the buffer. The server will respond with an input_audio_buffer.cleared event.
  - ofOutputAudioBufferClear
```
 final static RealtimeClientEvent ofOutputAudioBufferClear(OutputAudioBufferClearEvent outputAudioBufferClear)
```
    WebRTC Only: Emit to cut off the current audio response. This will trigger the server to stop generating audio and emit a output_audio_buffer.cleared event. This event should be preceded by a response.cancel client event to stop the generation of the current response. Learn more.
  - ofInputAudioBufferCommit
```
 final static RealtimeClientEvent ofInputAudioBufferCommit(InputAudioBufferCommitEvent inputAudioBufferCommit)
```
    Send this event to commit the user input audio buffer, which will create a new user message item in the conversation. This event will produce an error if the input audio buffer is empty. When in Server VAD mode, the client does not need to send this event, the server will commit the audio buffer automatically.
    Committing the input audio buffer will trigger input audio transcription (if enabled in session configuration), but it will not create a response from the model. The server will respond with an input_audio_buffer.committed event.
  - ofResponseCancel
```
 final static RealtimeClientEvent ofResponseCancel(ResponseCancelEvent responseCancel)
```
    Send this event to cancel an in-progress response. The server will respond with a response.done event with a status of response.status=cancelled. If there is no response to cancel, the server will respond with an error.
  - ofResponseCreate
```
 final static RealtimeClientEvent ofResponseCreate(ResponseCreateEvent responseCreate)
```
    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.
  - ofSessionUpdate
```
 final static RealtimeClientEvent ofSessionUpdate(SessionUpdateEvent sessionUpdate)
```
    Send this event to update the session’s default configuration. The client may send this event at any time to update any field, except for voice. However, note that once a session has been initialized with a particular model, it can’t be changed to another model using session.update.
    When the server receives a session.update, it will respond with a session.updated event showing the full, effective configuration. Only the fields that are present are updated. To clear a field like instructions, pass an empty string.
  - ofTranscriptionSessionUpdate
```
 final static RealtimeClientEvent ofTranscriptionSessionUpdate(TranscriptionSessionUpdate transcriptionSessionUpdate)
```
    Send this event to update a transcription session.

Class RealtimeClientEvent

Nested Class Summary

Field Summary

Constructor Summary

Enum Constant Summary

Method Summary

Methods inherited from class java.lang.Object

Constructor Detail

Method Detail

conversationItemCreate

conversationItemDelete

conversationItemRetrieve

conversationItemTruncate

inputAudioBufferAppend

inputAudioBufferClear

outputAudioBufferClear

inputAudioBufferCommit

responseCancel

responseCreate

sessionUpdate

transcriptionSessionUpdate

isConversationItemCreate

isConversationItemDelete

isConversationItemRetrieve

isConversationItemTruncate

isInputAudioBufferAppend

isInputAudioBufferClear

isOutputAudioBufferClear

isInputAudioBufferCommit

isResponseCancel

isResponseCreate

isSessionUpdate

isTranscriptionSessionUpdate

asConversationItemCreate

asConversationItemDelete

asConversationItemRetrieve

asConversationItemTruncate

asInputAudioBufferAppend

asInputAudioBufferClear

asOutputAudioBufferClear

asInputAudioBufferCommit

asResponseCancel

asResponseCreate

asSessionUpdate

asTranscriptionSessionUpdate

_json

accept

validate

isValid

equals

hashCode

toString

ofConversationItemCreate

ofConversationItemDelete

ofConversationItemRetrieve

ofConversationItemTruncate

ofInputAudioBufferAppend

ofInputAudioBufferClear

ofOutputAudioBufferClear

ofInputAudioBufferCommit

ofResponseCancel

ofResponseCreate

ofSessionUpdate

ofTranscriptionSessionUpdate