Variant of the specified [Speech
model][google.cloud.dialogflow.cx.v3beta1.InputAudioConfig.model] to
use.
See the Cloud Speech
documentation <https://cloud.google.com/speech-to-text/docs/enhanced-models>__
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.
- If an enhanced variant does not exist for the given
<xref uid="google.cloud.dialogflow.cx.v3beta1.InputAudioConfig.model">model</xref>
and request language, Dialogflow falls back to the
standard variant.
The `Cloud Speech
documentation <https://cloud.google.com/speech-to-text/docs/enhanced-models>`__
describes which models have enhanced variants.
Enums
Name
Description
SPEECH_MODEL_VARIANT_UNSPECIFIED
No model variant specified. In this case Dialogflow defaults to USE_BEST_AVAILABLE.
USE_BEST_AVAILABLE
Use the best available variant of the [Speech model][InputAudioConfig.model] that the caller is eligible for.
USE_STANDARD
Use standard model variant even if an enhanced model is available. See the `Cloud Speech documentation
[[["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 2025-08-28 UTC."],[],[],null,["# Class SpeechModelVariant (1.42.0)\n\nVersion latestkeyboard_arrow_down\n\n- [1.42.0 (latest)](/python/docs/reference/dialogflow-cx/latest/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.41.1](/python/docs/reference/dialogflow-cx/1.41.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.40.0](/python/docs/reference/dialogflow-cx/1.40.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.39.0](/python/docs/reference/dialogflow-cx/1.39.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.38.0](/python/docs/reference/dialogflow-cx/1.38.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.37.0](/python/docs/reference/dialogflow-cx/1.37.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.36.0](/python/docs/reference/dialogflow-cx/1.36.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.35.0](/python/docs/reference/dialogflow-cx/1.35.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.34.1](/python/docs/reference/dialogflow-cx/1.34.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.33.0](/python/docs/reference/dialogflow-cx/1.33.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.32.1](/python/docs/reference/dialogflow-cx/1.32.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.31.1](/python/docs/reference/dialogflow-cx/1.31.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.30.1](/python/docs/reference/dialogflow-cx/1.30.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.29.0](/python/docs/reference/dialogflow-cx/1.29.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.28.0](/python/docs/reference/dialogflow-cx/1.28.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.27.0](/python/docs/reference/dialogflow-cx/1.27.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.26.0](/python/docs/reference/dialogflow-cx/1.26.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.25.0](/python/docs/reference/dialogflow-cx/1.25.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.24.0](/python/docs/reference/dialogflow-cx/1.24.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.23.1](/python/docs/reference/dialogflow-cx/1.23.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.22.0](/python/docs/reference/dialogflow-cx/1.22.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.21.0](/python/docs/reference/dialogflow-cx/1.21.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.20.1](/python/docs/reference/dialogflow-cx/1.20.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.19.0](/python/docs/reference/dialogflow-cx/1.19.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.18.0](/python/docs/reference/dialogflow-cx/1.18.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.17.1](/python/docs/reference/dialogflow-cx/1.17.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.16.0](/python/docs/reference/dialogflow-cx/1.16.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.15.0](/python/docs/reference/dialogflow-cx/1.15.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.14.1](/python/docs/reference/dialogflow-cx/1.14.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.13.5](/python/docs/reference/dialogflow-cx/1.13.5/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.12.1](/python/docs/reference/dialogflow-cx/1.12.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.11.0](/python/docs/reference/dialogflow-cx/1.11.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.10.0](/python/docs/reference/dialogflow-cx/1.10.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.9.1](/python/docs/reference/dialogflow-cx/1.9.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.8.0](/python/docs/reference/dialogflow-cx/1.8.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.7.0](/python/docs/reference/dialogflow-cx/1.7.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.6.0](/python/docs/reference/dialogflow-cx/1.6.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.5.0](/python/docs/reference/dialogflow-cx/1.5.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.4.0](/python/docs/reference/dialogflow-cx/1.4.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.3.2](/python/docs/reference/dialogflow-cx/1.3.2/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.2.0](/python/docs/reference/dialogflow-cx/1.2.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.1.1](/python/docs/reference/dialogflow-cx/1.1.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [1.0.0](/python/docs/reference/dialogflow-cx/1.0.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [0.8.2](/python/docs/reference/dialogflow-cx/0.8.2/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [0.7.1](/python/docs/reference/dialogflow-cx/0.7.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [0.6.0](/python/docs/reference/dialogflow-cx/0.6.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [0.5.0](/python/docs/reference/dialogflow-cx/0.5.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [0.4.1](/python/docs/reference/dialogflow-cx/0.4.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [0.3.0](/python/docs/reference/dialogflow-cx/0.3.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [0.2.0](/python/docs/reference/dialogflow-cx/0.2.0/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant)\n- [0.1.1](/python/docs/reference/dialogflow-cx/0.1.1/google.cloud.dialogflowcx_v3beta1.types.SpeechModelVariant) \n\n SpeechModelVariant(value)\n\nVariant of the specified \\[Speech\nmodel\\]\\[google.cloud.dialogflow.cx.v3beta1.InputAudioConfig.model\\] to\nuse.\n\nSee the `Cloud Speech\ndocumentation \u003chttps://cloud.google.com/speech-to-text/docs/enhanced-models\u003e`__\nfor which models have different variants. For example, the\n\"phone_call\" model has both a standard and an enhanced variant. When\nyou use an enhanced model, you will generally receive higher quality\nresults than for a standard model. \n\n - If an enhanced variant does not exist for the given\n \u003cxref uid=\"google.cloud.dialogflow.cx.v3beta1.InputAudioConfig.model\"\u003emodel\u003c/xref\u003e\n and request language, Dialogflow falls back to the\n standard variant.\n\n The `Cloud Speech\n documentation \u003chttps://cloud.google.com/speech-to-text/docs/enhanced-models\u003e`__\n describes which models have enhanced variants."]]