The confidence estimate between 0.0 and 1.0. A higher number
indicates an estimated greater likelihood that the recognized words are
correct. This field is set only for the top alternative of a non-streaming
result or, of a streaming result where
[is_final][google.cloud.speech.v2.StreamingRecognitionResult.is_final] is
set to true. This field is not guaranteed to be accurate and users should
not rely on it to be always provided. The default of 0.0 is a sentinel
value indicating confidence was not set.
Time offset relative to the beginning of the audio,
and corresponding to the end of the spoken word.
This field is only set if
[enable_word_time_offsets][google.cloud.speech.v2.RecognitionFeatures.enable_word_time_offsets]
is true and only in the top hypothesis. This is an experimental feature
and the accuracy of the time offset can vary.
A distinct label is assigned for every speaker within the audio. This field
specifies which one of those speakers was detected to have spoken this
word. speaker_label is set if
[SpeakerDiarizationConfig][google.cloud.speech.v2.SpeakerDiarizationConfig]
is given and only in the top alternative.
Time offset relative to the beginning of the audio,
and corresponding to the start of the spoken word.
This field is only set if
[enable_word_time_offsets][google.cloud.speech.v2.RecognitionFeatures.enable_word_time_offsets]
is true and only in the top hypothesis. This is an experimental feature
and the accuracy of the time offset can vary.
[[["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complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-07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\u003eThe \u003ccode\u003eWordInfo\u003c/code\u003e class in the Google Cloud Speech-to-Text v2 API provides word-specific information for recognized words, and is available in versions 1.0.0 through 1.4.0 of the API.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003eWordInfo\u003c/code\u003e includes properties like \u003ccode\u003eConfidence\u003c/code\u003e, \u003ccode\u003eStartOffset\u003c/code\u003e, \u003ccode\u003eEndOffset\u003c/code\u003e, \u003ccode\u003eSpeakerLabel\u003c/code\u003e, and \u003ccode\u003eWord\u003c/code\u003e, which detail aspects of the recognized word such as its accuracy, timing, and speaker identity.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eConfidence\u003c/code\u003e property provides an estimated likelihood of word correctness, while \u003ccode\u003eStartOffset\u003c/code\u003e and \u003ccode\u003eEndOffset\u003c/code\u003e indicate the timing of the spoken word within the audio, when enabled.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eSpeakerLabel\u003c/code\u003e property identifies the detected speaker for a particular word when speaker diarization is configured.\u003c/p\u003e\n"],["\u003cp\u003eThe class \u003ccode\u003eWordInfo\u003c/code\u003e implements the interfaces \u003ccode\u003eIMessage\u003c/code\u003e, \u003ccode\u003eIEquatable\u003c/code\u003e, \u003ccode\u003eIDeepCloneable\u003c/code\u003e, and \u003ccode\u003eIBufferMessage\u003c/code\u003e, inheriting basic methods such as \u003ccode\u003eGetHashCode\u003c/code\u003e, \u003ccode\u003eGetType\u003c/code\u003e, and \u003ccode\u003eToString\u003c/code\u003e.\u003c/p\u003e\n"]]],[],null,[]]
