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=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=true and only
in the top hypothesis.
This is an experimental feature and the accuracy of the time offset can
vary.
Output only. A label value assigned for every unique speaker within the
audio. This field specifies which speaker was detected to have spoken this
word. For some models, like medical_conversation this can be actual speaker
role, for example "patient" or "provider", but generally this would be a
number identifying a speaker. This field is only set if
enable_speaker_diarization = 'true' and only for the top alternative.
Output only. A distinct integer value is assigned for every speaker within
the audio. This field specifies which one of those speakers was detected to
have spoken this word. Value ranges from '1' to diarization_speaker_count.
speaker_tag is set if enable_speaker_diarization = 'true' and only for the
top alternative.
Note: Use speaker_label instead.
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=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complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-07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 v1p1beta1 API provides word-specific information for recognized words, inheriting from \u003ccode\u003eobject\u003c/code\u003e and implementing multiple interfaces like \u003ccode\u003eIMessage\u003c/code\u003e, \u003ccode\u003eIEquatable\u003c/code\u003e, and \u003ccode\u003eIDeepCloneable\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eThe class is documented within the \u003ccode\u003eGoogle.Cloud.Speech.V1P1Beta1\u003c/code\u003e namespace and can be found within the \u003ccode\u003eGoogle.Cloud.Speech.V1P1Beta1.dll\u003c/code\u003e assembly.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003eWordInfo\u003c/code\u003e objects contain properties such as \u003ccode\u003eConfidence\u003c/code\u003e, \u003ccode\u003eEndTime\u003c/code\u003e, \u003ccode\u003eSpeakerTag\u003c/code\u003e, \u003ccode\u003eStartTime\u003c/code\u003e, and \u003ccode\u003eWord\u003c/code\u003e, which offer details like the confidence level of word recognition, time offsets for the word's beginning and end, and speaker identification.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eWordInfo\u003c/code\u003e class has two constructors, a default constructor \u003ccode\u003eWordInfo()\u003c/code\u003e and another, \u003ccode\u003eWordInfo(WordInfo other)\u003c/code\u003e, that accepts a \u003ccode\u003eWordInfo\u003c/code\u003e object as a parameter.\u003c/p\u003e\n"],["\u003cp\u003eThere are three different versions of the API available, including 3.0.0-beta08 (latest), 3.0.0-beta07, and 2.0.0-beta09, all with their respective documentation pages.\u003c/p\u003e\n"]]],[],null,["# Google Cloud Speech v1p1beta1 API - Class WordInfo (3.0.0-beta09)\n\nVersion latestkeyboard_arrow_down\n\n- [3.0.0-beta09 (latest)](/dotnet/docs/reference/Google.Cloud.Speech.V1P1Beta1/latest/Google.Cloud.Speech.V1P1Beta1.WordInfo)\n- [3.0.0-beta08](/dotnet/docs/reference/Google.Cloud.Speech.V1P1Beta1/3.0.0-beta08/Google.Cloud.Speech.V1P1Beta1.WordInfo)\n- [2.0.0-beta09](/dotnet/docs/reference/Google.Cloud.Speech.V1P1Beta1/2.0.0-beta09/Google.Cloud.Speech.V1P1Beta1.WordInfo) \n\n public sealed class WordInfo : IMessage\u003cWordInfo\u003e, IEquatable\u003cWordInfo\u003e, IDeepCloneable\u003cWordInfo\u003e, IBufferMessage, IMessage\n\nReference documentation and code samples for the Google Cloud Speech v1p1beta1 API class WordInfo.\n\nWord-specific information for recognized words. \n\nInheritance\n-----------\n\n[object](https://learn.microsoft.com/dotnet/api/system.object) \\\u003e WordInfo \n\nImplements\n----------\n\n[IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage-1.html)[WordInfo](/dotnet/docs/reference/Google.Cloud.Speech.V1P1Beta1/latest/Google.Cloud.Speech.V1P1Beta1.WordInfo), [IEquatable](https://learn.microsoft.com/dotnet/api/system.iequatable-1)[WordInfo](/dotnet/docs/reference/Google.Cloud.Speech.V1P1Beta1/latest/Google.Cloud.Speech.V1P1Beta1.WordInfo), [IDeepCloneable](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IDeepCloneable-1.html)[WordInfo](/dotnet/docs/reference/Google.Cloud.Speech.V1P1Beta1/latest/Google.Cloud.Speech.V1P1Beta1.WordInfo), [IBufferMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IBufferMessage.html), [IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage.html) \n\nInherited Members\n-----------------\n\n[object.GetHashCode()](https://learn.microsoft.com/dotnet/api/system.object.gethashcode) \n[object.GetType()](https://learn.microsoft.com/dotnet/api/system.object.gettype) \n[object.ToString()](https://learn.microsoft.com/dotnet/api/system.object.tostring)\n\nNamespace\n---------\n\n[Google.Cloud.Speech.V1P1Beta1](/dotnet/docs/reference/Google.Cloud.Speech.V1P1Beta1/latest/Google.Cloud.Speech.V1P1Beta1)\n\nAssembly\n--------\n\nGoogle.Cloud.Speech.V1P1Beta1.dll\n\nConstructors\n------------\n\n### WordInfo()\n\n public WordInfo()\n\n### WordInfo(WordInfo)\n\n public WordInfo(WordInfo other)\n\nProperties\n----------\n\n### Confidence\n\n public float Confidence { get; set; }\n\nThe confidence estimate between 0.0 and 1.0. A higher number\nindicates an estimated greater likelihood that the recognized words are\ncorrect. This field is set only for the top alternative of a non-streaming\nresult or, of a streaming result where `is_final=true`.\nThis field is not guaranteed to be accurate and users should not rely on it\nto be always provided.\nThe default of 0.0 is a sentinel value indicating `confidence` was not set.\n\n### EndTime\n\n public Duration EndTime { get; set; }\n\nTime offset relative to the beginning of the audio,\nand corresponding to the end of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.\n\n### SpeakerLabel\n\n public string SpeakerLabel { get; set; }\n\nOutput only. A label value assigned for every unique speaker within the\naudio. This field specifies which speaker was detected to have spoken this\nword. For some models, like medical_conversation this can be actual speaker\nrole, for example \"patient\" or \"provider\", but generally this would be a\nnumber identifying a speaker. This field is only set if\nenable_speaker_diarization = 'true' and only for the top alternative.\n\n### SpeakerTag\n\n [Obsolete]\n public int SpeakerTag { get; set; }\n\nOutput only. A distinct integer value is assigned for every speaker within\nthe audio. This field specifies which one of those speakers was detected to\nhave spoken this word. Value ranges from '1' to diarization_speaker_count.\nspeaker_tag is set if enable_speaker_diarization = 'true' and only for the\ntop alternative.\nNote: Use speaker_label instead.\n\n### StartTime\n\n public Duration StartTime { get; set; }\n\nTime offset relative to the beginning of the audio,\nand corresponding to the start of the spoken word.\nThis field is only set if `enable_word_time_offsets=true` and only\nin the top hypothesis.\nThis is an experimental feature and the accuracy of the time offset can\nvary.\n\n### Word\n\n public string Word { get; set; }\n\nThe word corresponding to this set of information."]]
