Class SpeechModelVariant (1.21.0)

SpeechModelVariant(value)

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.

Values: SPEECH_MODEL_VARIANT_UNSPECIFIED (0): No model variant specified. In this case Dialogflow defaults to USE_BEST_AVAILABLE. USE_BEST_AVAILABLE (1): Use the best available variant of the [Speech model][InputAudioConfig.model] that the caller is eligible for.

    Please see the `Dialogflow
    docs <https://cloud.google.com/dialogflow/docs/data-logging>`__
    for how to make your project eligible for enhanced models.
USE_STANDARD (2):
    Use standard model variant even if an enhanced model is
    available. See the `Cloud Speech
    documentation <https://cloud.google.com/speech-to-text/docs/enhanced-models>`__
    for details about enhanced models.
USE_ENHANCED (3):
    Use an enhanced model variant:

    -  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.

    -  If the API caller isn't eligible for enhanced models,
       Dialogflow returns an error. Please see the `Dialogflow
       docs <https://cloud.google.com/dialogflow/docs/data-logging>`__
       for how to make your project eligible.