Reference documentation and code samples for the Dialogflow v3 API enum SpeechModelVariant.
Variant of the specified [Speech
model][google.cloud.dialogflow.cx.v3.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.
UseEnhanced
Use an enhanced model variant:
If an enhanced variant does not exist for the given
[model][google.cloud.dialogflow.cx.v3.InputAudioConfig.model] and request
language, Dialogflow falls back to the standard variant.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-04-09 UTC."],[[["This page provides documentation for the `SpeechModelVariant` enum within the Google Cloud Dialogflow CX v3 API, detailing the different versions and available model variants for speech recognition."],["The latest version of the documentation is 2.23.0, and the page lists a comprehensive history of versions, ranging from 2.23.0 down to 1.0.0."],["The `SpeechModelVariant` enum allows users to specify whether they want to use the best available, enhanced, or standard variant of a speech model, as described in the Cloud Speech documentation."],["The available fields within the enum are `Unspecified`, `UseBestAvailable`, `UseEnhanced`, and `UseStandard`, each providing a different approach to selecting the speech model variant during speech-to-text conversion."]]],[]]
