The top-level message sent by the client to the [Sessions.StreamingDet ectIntent][google.cloud.dialogflow.v2beta1.Sessions.StreamingDetectInt ent] method. Multiple request messages should be sent in order: 1. The first message must contain [session][google.cloud.dialogflow.v2 beta1.StreamingDetectIntentRequest.session], [query_input][google.c loud.dialogflow.v2beta1.StreamingDetectIntentRequest.query_input] plus optionally [query_params][google.cloud.dialogflow.v2beta1.Stre amingDetectIntentRequest.query_params]. If the client wants to receive an audio response, it should also contain [output_audio_ config][google.cloud.dialogflow.v2beta1.StreamingDetectIntentRequest.o utput_audio_config]. The message must not contain [input_audio][ google.cloud.dialogflow.v2beta1.StreamingDetectIntentRequest.input_aud io]. 2. If [query_input][google.cloud.dialogflow.v2beta1.StreamingD etectIntentRequest.query_input] was set to [query_input.audio_co nfig][google.cloud.dialogflow.v2beta1.InputAudioConfig], all subsequent messages must contain [input_audio][google.cloud.dialogf low.v2beta1.StreamingDetectIntentRequest.input_audio] to continue with Speech recognition. If you decide to rather detect an intent from text input after you already started Speech recognition, please send a message with query_input.text. However, note that: - Dialogflow will bill you for the audio duration so far. - Dialogflow discards all Speech recognition results in favor of the input text. - Dialogflow will use the language code from the first message. After you sent all input, you must half-close or abort the request stream.
The parameters of this query.
DEPRECATED. Please use [InputAudioConfig.single_utterance][goo
gle.cloud.dialogflow.v2beta1.InputAudioConfig.single_utterance
] instead. If false (default), recognition does not cease
until the client closes the stream. If true, the
recognizer will detect a single spoken utterance in input
audio. Recognition ceases when it detects the audio’s voice
has stopped or paused. In this case, once a detected intent is
received, the client should close the stream and start a new
request with a new stream as needed. This setting is ignored
when query_input is a piece of text or an event.
Mask for [output_audio_config][google.cloud.dialogflow.v2beta1 .StreamingDetectIntentRequest.output_audio_config] indicating which settings in this request-level config should override speech synthesizer settings defined at agent-level. If unspecified or empty, [output_audio_config][google.cloud.dialo gflow.v2beta1.StreamingDetectIntentRequest.output_audio_config ] replaces the agent-level config in its entirety.