Some or all of the information on this page might not apply to Cloud de Confiance by S3NS. See Differences from Google Cloud for more details.

Class VoiceSessionConfig (2.52.0)

VoiceSessionConfig(mapping=None, *, ignore_unknown_fields=False, **kwargs)

The config about how to process the audio for a voice-based session.

Attributes
Name	Description
`input_audio_encoding`	`google.cloud.dialogflow_v2.types.AudioEncoding` Required. The encoding of input audio.
`input_audio_sample_rate_hertz`	`int` Required. The sample rate of input audio.
`output_audio_encoding`	`google.cloud.dialogflow_v2.types.OutputAudioEncoding` Required. The encoding of output audio.
`output_audio_sample_rate_hertz`	`int` Required. The sample rate of output audio.
`enable_cx_proactive_processing`	`bool` Optional. Whether to enable CX proactive processing.
`enable_streaming_synthesize`	`bool` Optional. If true, Dialogflow will stream the audio bytes from Cloud TTS for speech synthesis using the StreamingSynthesize api.
`gemini_asr_config`	`google.cloud.dialogflow_v2.types.SpeechToTextConfig.GeminiAsrConfig` Optional. Configuration for using Gemini ASR models served via Vertex AI. This field is only used when `use_gemini_asr` is true.
`use_gemini_asr`	`bool` Optional. If true, Gemini ASR will be used for transcription instead of Cloud Speech-to-Text. If false, Cloud Speech-to-Text will be used. If unset, this setting is inherited from the ConversationProfile. This field is a member of `oneof`_ `_use_gemini_asr`.

Attributes