/queryParams/timeZone |
A time zone from the time zone database. |
Sets the time zone for conversational requests. Applicable to Voice and Digital interactions. |
/audioConfig/enableWordInfo |
- |
When true, recognition results include information about the recognized speech words. Applicable to Voice interactions. |
/audioConfig/model |
Tag for one of Google Dialogflow speech-to-text models. |
Controls the speech-to-text model used for streaming audio requests. Applicable to Voice interactions. |
/audioConfig/modelVariant |
USE_BEST_AVAILABLE: Uses the best variant available for the chosen model. USE_STANDARD: Uses only the standard model variant. USE_ENHANCED: Uses the enhanced model variant, if available. Returns an error if enhanced models are not enabled in the project. |
Determines the speech-to-text model variant used for streaming audio requests. Applicable to Voice interactions. |
/outputAudioConfig/synthesizeSpeechConfig/speakingRate |
The valid value is 0.25 to 4.0. The default value is 1.0. |
Sets the speaking rate for a generated TTS audio. Applicable to Voice interactions. |
/outputAudioConfig/synthesizeSpeechConfig/pitch |
The valid value is -20.0 to 20.0. The default value is 0.0. |
Sets the speaking pitch for a generated TTS audio. Applicable to Voice interactions. |
/outputAudioConfig/synthesizeSpeechConfig/volumeGainDb |
The valid value is -96.0 to 16.0. The default value is 0.0. |
Adjusts the volume for a generated TTS audio. Applicable to Voice interactions. |
/outputAudioConfig/synthesizeSpeechConfig/effectsProfileId[] |
A comma-separated list of audio profile IDs. |
Selects the audio effects profiles that Google Dialogflow applies to a generated TTS audio. Applicable to Voice interactions. |
/outputAudioConfig/synthesizeSpeechConfig/voice/name |
A voice name for a Google TTS voice. |
Determines the voice that Google Dialogflow uses to generate a TTS audio. The specified voice must correspond with the default language setting. Applicable to Voice interactions. |
/outputAudioConfig/synthesizeSpeechConfig/voice/ssmlGender |
SSML_VOICE_GENDER_MALE: Google Dialogflow uses a male voice. SSML_VOICE_GENDER_FEMALE: Google Dialogflow uses a female voice. SSML_VOICE_GENDER_NEUTRAL: Google Dialogflow uses a gender-neutral voice. |
Sets the preferred gender of the voice that Google Dialogflow uses to generate a TTS audio. Only applied if the specified gender is available for the selected language. To set the gender, ensure the /outputAudioConfig/synthesizeSpeechConfig/voice/name and outputAudioConfig.synthesizeSpeechConfig.voice.customVoice.model parameters are not set. Applicable to Voice interactions. |
/outputAudioConfig/synthesizeSpeechConfig/voice/ customVoice/model |
Name of an AutoML model. |
Sets the custom voice model that Google Dialogflow uses to generate TTS audio. Applicable to Voice interactions. |
/outputAudioConfig/synthesizeSpeechConfig/voice/ customVoice/reportedUsage |
|
Specifies the usage of the TTS audio for the custom voice. Applicable to Voice interactions. |
/vadMode |
Disabled: Bypasses the platform VAD. All audio data, including silence, is sent to Google Dialogflow for analysis. Hybrid: Uses platform VAD to eliminate leading silence from speech utterances. |
The controls when the platform VAD is engaged to regulate the audio data sent to Google Dialogflow. The default is hybrid. Applicable to Voice interactions. |
/term/event/name |
An event name from Dialogflow Agent. |
The input event to the Google Dialogflow application when the dialog terminates. Applicable to Voice interactions. |
/term/intent/id |
An intent ID from the Dialogflow Agent. |
The input intent to the Google Dialogflow application when the dialog terminates. Applicable to Voice interactions. |
