Understanding the Flux State Machine
Traditional STT+VAD requires you to build complex interruption logic. Flux handles this natively.
Emitted events adhere to the below state machine for managing turns:
Updatemessages are sent for approximately every 0.25 seconds of transcribed audio, regardless of transcript updates, unless a state change has occurred.- An
EagerEndOfTurnmessage always contains a nonempty transcript. - A
TurnResumedmessage can only follow a precedingEagerEndOfTurnmessage. - The
EndOfTurntranscript will always match the immediately precedingEagerEndOfTurntranscript. If the transcript changes after anEagerEndOfTurn, aTurnResumedevent will occur first. - The
turn_indexincrements immediately following anEndOfTurnmessage.
Configuring Event Behavior: The EagerEndOfTurn and TurnResumed events are only triggered when you set the eager_eot_threshold parameter. The EndOfTurn event behavior is controlled by eot_threshold and eot_timeout_ms parameters. See the End-of-Turn Configuration for details on tuning these thresholds for your use case.
Turn Lifecycle Example
Here’s how Flux processes a customer calling support saying “Hi I need to cancel my subscription please.”
Notice how confidence builds up and how the EagerEndOfTurn event fires before the final EndOfTurn. With EagerEndOfTurn, your voice agent can begin preparing a response before the user has fully finished speaking. This allows you to send a synchronous request with early context, creating the effect of a faster, more natural reply.