Variant of the specified [Speech model][google.cloud.dialogflow.v2.InputAudioConfig.model] to use.
See the Cloud Speech
documentation
for which models have different variants. For example, the "phone_call" model
has both a standard and an enhanced variant. When you use an enhanced model,
you will generally receive higher quality results than for a standard model.
No model variant specified. In this case Dialogflow defaults to
USE_BEST_AVAILABLE.
UseBestAvailable
Use the best available variant of the [Speech
model][InputAudioConfig.model] that the caller is eligible for.
Please see the Dialogflow
docs for
how to make your project eligible for enhanced models.
UseEnhanced
Use an enhanced model variant:
If an enhanced variant does not exist for the given
[model][google.cloud.dialogflow.v2.InputAudioConfig.model] and request language, Dialogflow falls
back to the standard variant.
If the API caller isn't eligible for enhanced models, Dialogflow returns
an error. Please see the Dialogflow
docs
for how to make your project eligible.
UseStandard
Use standard model variant even if an enhanced model is available. See the
Cloud Speech
documentation
for details about enhanced models.
[[["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complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-07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 webpage details the \u003ccode\u003eSpeechModelVariant\u003c/code\u003e enum within the Google.Cloud.Dialogflow.V2 namespace, outlining different speech model variants available for use with Dialogflow.\u003c/p\u003e\n"],["\u003cp\u003eThe latest version documented is 4.26.0, with a comprehensive list of previous versions down to 3.2.0 available, all hyperlinked.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eSpeechModelVariant\u003c/code\u003e enum has four fields: \u003ccode\u003eUnspecified\u003c/code\u003e, \u003ccode\u003eUseBestAvailable\u003c/code\u003e, \u003ccode\u003eUseEnhanced\u003c/code\u003e, and \u003ccode\u003eUseStandard\u003c/code\u003e, each with descriptions on how Dialogflow handles the variants, the best way to determine how to use them, and when to expect errors or fallbacks.\u003c/p\u003e\n"],["\u003cp\u003eThe documentation links to the Cloud Speech documentation for information about enhanced models, and it also links to the Dialogflow documentation for how to become eligible for these enhanced models.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eSpeechModelVariant\u003c/code\u003e will determine which model of speech recognition is being utilized, with options being 'best available', 'enhanced', or 'standard', and it's stated that if the model is left unspecified, it will default to 'best available'.\u003c/p\u003e\n"]]],[],null,[]]
