This event indicates that the server has detected the end of the user's
speech utterance and expects no additional speech. Therefore, the server
will not process additional audio and will close the gRPC bidirectional
stream. This event is only sent if there was a force cutoff due to
silence being detected early. This event is only available through the
latest_short [model][google.cloud.speech.v2.Recognizer.model].
SpeechActivityBegin
This event indicates that the server has detected the beginning of human
voice activity in the stream. This event can be returned multiple times
if speech starts and stops repeatedly throughout the stream. This event
is only sent if voice_activity_events is set to true.
SpeechActivityEnd
This event indicates that the server has detected the end of human voice
activity in the stream. This event can be returned multiple times if
speech starts and stops repeatedly throughout the stream. This event is
only sent if voice_activity_events is set to true.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-07 UTC."],[[["\u003cp\u003eThis documentation outlines the \u003ccode\u003eStreamingRecognizeResponse.Types.SpeechEventType\u003c/code\u003e enum for the Cloud Speech-to-Text v2 API, which indicates the type of speech event detected.\u003c/p\u003e\n"],["\u003cp\u003eThe latest version of this API is 1.4.0, and versions 1.0.0 through 1.3.0 are also documented.\u003c/p\u003e\n"],["\u003cp\u003eThe enum defines four fields: \u003ccode\u003eEndOfSingleUtterance\u003c/code\u003e, which indicates the end of speech; \u003ccode\u003eSpeechActivityBegin\u003c/code\u003e and \u003ccode\u003eSpeechActivityEnd\u003c/code\u003e, which mark the start and end of voice activity; and \u003ccode\u003eUnspecified\u003c/code\u003e, for when no speech event is identified.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eEndOfSingleUtterance\u003c/code\u003e event signals that no more speech is expected and will only be sent if a force cutoff is detected, whereas \u003ccode\u003eSpeechActivityBegin\u003c/code\u003e and \u003ccode\u003eSpeechActivityEnd\u003c/code\u003e are sent when \u003ccode\u003evoice_activity_events\u003c/code\u003e is set to true, indicating the beginning and end of voice activity.\u003c/p\u003e\n"]]],[],null,[]]
