LiveServerContent

LiveServerContent(
    content: Content?,
    interrupted: Boolean,
    turnComplete: Boolean,
    generationComplete: Boolean,
    inputTranscription: Transcription?,
    outputTranscription: Transcription?
)

content

val content: Content?

The content that the model has generated as part of the current conversation with the user.

This can benull if there is no content.

generationComplete

val generationComplete: Boolean

The model has finishedgenerating data for the current turn.

For realtime playback, there will be a delay between when the model finishes generating content and the client has finished playing back the generated content.generationComplete indicates that the model is done generating data, whileturnComplete indicates the model is waiting for additional client messages. Sending a message during this delay may cause aninterrupted message to be sent.

Note that if the model wasinterrupted, this will not be set. The model will go frominterrupted ->turnComplete.

inputTranscription

val inputTranscription: Transcription?

The input transcription. The transcription is independent to the model turn which means it doesn't imply any ordering between transcription and model turn.

interrupted

val interrupted: Boolean

The model was interrupted by the client while generating data.

An interruption occurs when the client sends a message while the model is actively sending data.

outputTranscription

val outputTranscription: Transcription?

The output transcription. The transcription is independent to the model turn which means it doesn't imply any ordering between transcription and model turn.

turnComplete

val turnComplete: Boolean

The model has finished sending data in the current turn.

Generation will only start in response to additional client messages.

Can be set alongsidecontent, indicating that thecontent is the last in the turn.