IMPORTANT: In July 2025, we stopped releasing new versions of KTX modules, and we removed the KTX libraries from the Firebase Android BoM (v34.0.0). If you use KTX APIs from the previously released KTX modules, we recommend that you migrate your app to use KTX APIs from the main modules instead. For details, see the FAQ about this initiative.

LiveSession

@PublicPreviewAPI
public final class LiveSession

Represents a live WebSocket session capable of streaming content to and from the server.

Summary

Public methods
`final void`	`close()` Closes the client session.
`final boolean`	`isAudioConversationActive()` Indicates whether an audio conversation is being used for this session object.
`final boolean`	`isClosed()` Indicates whether the underlying websocket connection is active.
`final @NonNull Flow<@NonNull LiveServerMessage>`	`receive()` Receives responses from the model for both streaming and standard requests.
`final void`	`send(@NonNull Content content)` Sends `data` to the model.
`final void`	`send(@NonNull String text)` Sends text to the model.
`final void`	`sendAudioRealtime(@NonNull InlineData audio)` Sends an audio input stream to the model, using the realtime API.
`final void`	`sendFunctionResponse( @NonNull List<@NonNull FunctionResponsePart> functionList )` Sends function calling responses to the model.
`final void`	`sendMediaStream(@NonNull List<@NonNull MediaData> mediaChunks)` This method is deprecated. Use sendAudioRealtime, sendVideoRealtime, or sendTextRealtime instead
`final void`	`sendTextRealtime(@NonNull String text)` Sends a text input stream to the model, using the realtime API.
`final void`	`sendVideoRealtime(@NonNull InlineData video)` Sends a video frame to the model, using the realtime API.
`final void`	`@RequiresPermission(value = "android.permission.RECORD_AUDIO") startAudioConversation( Function1<@NonNull FunctionCallPart, @NonNull FunctionResponsePart> functionCallHandler )` Starts an audio conversation with the model, which can only be stopped using `stopAudioConversation` or `close`.
`final void`	`@RequiresPermission(value = "android.permission.RECORD_AUDIO") startAudioConversation( @NonNull LiveAudioConversationConfig liveAudioConversationConfig )` Starts an audio conversation with the model, which can only be stopped using `stopAudioConversation` or `close`.
`final void`	`@RequiresPermission(value = "android.permission.RECORD_AUDIO") startAudioConversation( Function1<@NonNull FunctionCallPart, @NonNull FunctionResponsePart> functionCallHandler, boolean enableInterruptions )` Starts an audio conversation with the model, which can only be stopped using `stopAudioConversation` or `close`.
`final void`	`@RequiresPermission(value = "android.permission.RECORD_AUDIO") startAudioConversation( Function1<@NonNull FunctionCallPart, @NonNull FunctionResponsePart> functionCallHandler, Function2<Transcription, Transcription, Unit> transcriptHandler, boolean enableInterruptions )` Starts an audio conversation with the model, which can only be stopped using `stopAudioConversation` or `close`.
`final void`	`@RequiresPermission(value = "android.permission.RECORD_AUDIO") startAudioConversation( Function1<@NonNull FunctionCallPart, @NonNull FunctionResponsePart> functionCallHandler, Function2<Transcription, Transcription, Unit> transcriptHandler, Function1<@NonNull LiveServerGoAway, Unit> goAwayHandler, boolean enableInterruptions )` Starts an audio conversation with the model, which can only be stopped using `stopAudioConversation` or `close`.
`final void`	`stopAudioConversation()` Stops the audio conversation with the model.
`final void`	`stopReceiving()` Stops receiving from the model.

Public methods

close

public final void close()

Closes the client session.

Once a LiveSession is closed, it can not be reopened; you'll need to start a new LiveSession.

See also
`stopReceiving`

isAudioConversationActive

public final boolean isAudioConversationActive()

Indicates whether an audio conversation is being used for this session object.

isClosed

public final boolean isClosed()

Indicates whether the underlying websocket connection is active.

receive

public final @NonNull Flow<@NonNull LiveServerMessage> receive()

Receives responses from the model for both streaming and standard requests.

Call close to stop receiving responses from the model.

Returns
`@NonNull Flow<@NonNull LiveServerMessage>`	A `Flow` which will emit `LiveServerMessage` from the model.

Throws
`com.google.firebase.ai.type.SessionAlreadyReceivingException com.google.firebase.ai.type.SessionAlreadyReceivingException`	when the session is already receiving.

See also
`stopReceiving`

send

public final void send(@NonNull Content content)

Sends data to the model.

Calling this after startAudioConversation will play the response audio immediately.

Parameters
`@NonNull Content content`	Client `Content` to be sent to the model.

send

public final void send(@NonNull String text)

Sends text to the model.

Calling this after startAudioConversation will play the response audio immediately.

Parameters
`@NonNull String text`	Text to be sent to the model.

sendAudioRealtime

public final void sendAudioRealtime(@NonNull InlineData audio)

Sends an audio input stream to the model, using the realtime API.

To learn more about audio formats, and the required state they should be provided in, see the docs on Supported audio formats

Parameters
`@NonNull InlineData audio`	Raw audio data used to update the model on the client's conversation. For best results, send 16-bit PCM audio at 24kHz.

sendFunctionResponse

public final void sendFunctionResponse(
    @NonNull List<@NonNull FunctionResponsePart> functionList
)

Sends function calling responses to the model.

NOTE: If you're using startAudioConversation, the method will handle sending function responses to the model for you. You do not need to call this method in that case.

Parameters
`@NonNull List<@NonNull FunctionResponsePart> functionList`	The list of `FunctionResponsePart` instances indicating the function response from the client.

sendMediaStream

public final void sendMediaStream(@NonNull List<@NonNull MediaData> mediaChunks)

Streams client data to the model.

Calling this after startAudioConversation will play the response audio immediately.

Parameters
`@NonNull List<@NonNull MediaData> mediaChunks`	The list of `MediaData` instances representing the media data to be sent.

sendTextRealtime

public final void sendTextRealtime(@NonNull String text)

Sends a text input stream to the model, using the realtime API.

Parameters
`@NonNull String text`	Text content to append to the current client's conversation.

sendVideoRealtime

public final void sendVideoRealtime(@NonNull InlineData video)

Sends a video frame to the model, using the realtime API.

Instead of raw video data, the model expects individual frames of the video, sent as images.

If your video has audio, send it separately through sendAudioRealtime.

For better performance, frames can also be sent at a lower rate than the video; even as low as 1 frame per second.

Parameters
`@NonNull InlineData video`	Encoded image data extracted from a frame of the video, used to update the model on the client's conversation, with the corresponding IANA standard MIME type of the video frame data (for example, `image/png`, `image/jpeg`, etc.).

startAudioConversation

@RequiresPermission(value = "android.permission.RECORD_AUDIO")
public final void startAudioConversation(
    Function1<@NonNull FunctionCallPart, @NonNull FunctionResponsePart> functionCallHandler
)

Starts an audio conversation with the model, which can only be stopped using stopAudioConversation or close.

Parameters
`Function1<@NonNull FunctionCallPart, @NonNull FunctionResponsePart> functionCallHandler`	A callback function that is invoked whenever the model receives a function call. The `FunctionResponsePart` that the callback function returns will be automatically sent to the model.

startAudioConversation

@RequiresPermission(value = "android.permission.RECORD_AUDIO")
public final void startAudioConversation(
    @NonNull LiveAudioConversationConfig liveAudioConversationConfig
)

Starts an audio conversation with the model, which can only be stopped using stopAudioConversation or close.

Parameters
`@NonNull LiveAudioConversationConfig liveAudioConversationConfig`	A `LiveAudioConversationConfig` provided by the user to control the various aspects of the conversation.

startAudioConversation

@RequiresPermission(value = "android.permission.RECORD_AUDIO")
public final void startAudioConversation(
    Function1<@NonNull FunctionCallPart, @NonNull FunctionResponsePart> functionCallHandler,
    boolean enableInterruptions
)

Starts an audio conversation with the model, which can only be stopped using stopAudioConversation or close.

Parameters

Function1<@NonNull FunctionCallPart, @NonNull FunctionResponsePart> functionCallHandler

A callback function that is invoked whenever the model receives a function call. The FunctionResponsePart that the callback function returns will be automatically sent to the model.

boolean enableInterruptions

If enabled, allows the user to speak over or interrupt the model's ongoing reply.

WARNING: The user interruption feature relies on device-specific support, and may not be consistently available.

startAudioConversation

@RequiresPermission(value = "android.permission.RECORD_AUDIO")
public final void startAudioConversation(
    Function1<@NonNull FunctionCallPart, @NonNull FunctionResponsePart> functionCallHandler,
    Function2<Transcription, Transcription, Unit> transcriptHandler,
    boolean enableInterruptions
)

Starts an audio conversation with the model, which can only be stopped using stopAudioConversation or close.

Parameters

Function1<@NonNull FunctionCallPart, @NonNull FunctionResponsePart> functionCallHandler

A callback function that is invoked whenever the model receives a function call. The FunctionResponsePart that the callback function returns will be automatically sent to the model.

Function2<Transcription, Transcription, Unit> transcriptHandler

A callback function that is invoked whenever the model receives a transcript. The first Transcription object is the input transcription, and the second is the output transcription.

boolean enableInterruptions

If enabled, allows the user to speak over or interrupt the model's ongoing reply.

WARNING: The user interruption feature relies on device-specific support, and may not be consistently available.

startAudioConversation

@RequiresPermission(value = "android.permission.RECORD_AUDIO")
public final void startAudioConversation(
    Function1<@NonNull FunctionCallPart, @NonNull FunctionResponsePart> functionCallHandler,
    Function2<Transcription, Transcription, Unit> transcriptHandler,
    Function1<@NonNull LiveServerGoAway, Unit> goAwayHandler,
    boolean enableInterruptions
)

Starts an audio conversation with the model, which can only be stopped using stopAudioConversation or close.

Parameters
`Function1<@NonNull FunctionCallPart, @NonNull FunctionResponsePart> functionCallHandler`	A callback function that is invoked whenever the model receives a function call. The `FunctionResponsePart` that the callback function returns will be automatically sent to the model.
`Function2<Transcription, Transcription, Unit> transcriptHandler`	A callback function that is invoked whenever the model receives a transcript. The first `Transcription` object is the input transcription, and the second is the output transcription.
`Function1<@NonNull LiveServerGoAway, Unit> goAwayHandler`	A callback function that is invoked when the server initiates a disconnect via a `LiveServerGoAway` message. This allows the application to handle server-initiated session termination gracefully.
`boolean enableInterruptions`	If enabled, allows the user to speak over or interrupt the model's ongoing reply. WARNING: The user interruption feature relies on device-specific support, and may not be consistently available.

stopAudioConversation

public final void stopAudioConversation()

Stops the audio conversation with the model.

This only needs to be called after a previous call to startAudioConversation.

If there is no audio conversation currently active, this function does nothing.

stopReceiving

public final void stopReceiving()

Stops receiving from the model.

If this function is called during an ongoing audio conversation, the model's response will not be received, and no audio will be played; the live session object will no longer receive data from the server.

To resume receiving data, you must either handle it directly using receive, or indirectly by using startAudioConversation.

See also
`close`