google-api-python-client 2.156.0__py2.py3-none-any.whl → 2.158.0__py2.py3-none-any.whl

googleapiclient/discovery_cache/documents/dialogflow.v3.json

@@ -4453,7 +4453,7 @@
 }
 }
 },
-"revision": "20241212",
+"revision": "20241216",
 "rootUrl": "https://dialogflow.googleapis.com/",
 "schemas": {
 "GoogleCloudDialogflowCxV3AdvancedSettings": {
@@ -12814,6 +12814,10 @@ false
 "$ref": "GoogleCloudDialogflowV2Message",
 "description": "Payload of NEW_MESSAGE event."
 },
+"newRecognitionResultPayload": {
+"$ref": "GoogleCloudDialogflowV2StreamingRecognitionResult",
+"description": "Payload of NEW_RECOGNITION_RESULT event."
+},
 "type": {
 "description": "The type of the event that this notification refers to.",
 "enum": [
@@ -12822,6 +12826,7 @@ false
 "CONVERSATION_FINISHED",
 "HUMAN_INTERVENTION_NEEDED",
 "NEW_MESSAGE",
+"NEW_RECOGNITION_RESULT",
 "UNRECOVERABLE_ERROR"
 ],
 "enumDescriptions": [
@@ -12830,6 +12835,7 @@ false
 "An existing conversation has closed. This is fired when a telephone call is terminated, or a conversation is closed via the API.",
 "An existing conversation has received notification from Dialogflow that human intervention is required.",
 "An existing conversation has received a new message, either from API or telephony. It is configured in ConversationProfile.new_message_event_notification_config",
+"An existing conversation has received a new speech recognition result. This is mainly for delivering intermediate transcripts. The notification is configured in ConversationProfile.new_recognition_event_notification_config.",
 "Unrecoverable error during a telephone call. In general non-recoverable errors only occur if something was misconfigured in the ConversationProfile corresponding to the call. After a non-recoverable error, Dialogflow may stop responding. We don't fire this event: * in an API call because we can directly return the error, or, * when we can recover from an error."
 ],
 "type": "string"
@@ -14729,6 +14735,82 @@ true
 },
 "type": "object"
 },
+"GoogleCloudDialogflowV2SpeechWordInfo": {
+"description": "Information for a word recognized by the speech recognizer.",
+"id": "GoogleCloudDialogflowV2SpeechWordInfo",
+"properties": {
+"confidence": {
+"description": "The Speech confidence between 0.0 and 1.0 for this word. A higher number indicates an estimated greater likelihood that the recognized word is correct. The default of 0.0 is a sentinel value indicating that confidence was not set. This field is not guaranteed to be fully stable over time for the same audio input. Users should also not rely on it to always be provided.",
+"format": "float",
+"type": "number"
+},
+"endOffset": {
+"description": "Time offset relative to the beginning of the audio that corresponds to the end of the spoken word. This is an experimental feature and the accuracy of the time offset can vary.",
+"format": "google-duration",
+"type": "string"
+},
+"startOffset": {
+"description": "Time offset relative to the beginning of the audio that corresponds to the start of the spoken word. This is an experimental feature and the accuracy of the time offset can vary.",
+"format": "google-duration",
+"type": "string"
+},
+"word": {
+"description": "The word this info is for.",
+"type": "string"
+}
+},
+"type": "object"
+},
+"GoogleCloudDialogflowV2StreamingRecognitionResult": {
+"description": "Contains a speech recognition result corresponding to a portion of the audio that is currently being processed or an indication that this is the end of the single requested utterance. While end-user audio is being processed, Dialogflow sends a series of results. Each result may contain a `transcript` value. A transcript represents a portion of the utterance. While the recognizer is processing audio, transcript values may be interim values or finalized values. Once a transcript is finalized, the `is_final` value is set to true and processing continues for the next transcript. If `StreamingDetectIntentRequest.query_input.audio_config.single_utterance` was true, and the recognizer has completed processing audio, the `message_type` value is set to `END_OF_SINGLE_UTTERANCE and the following (last) result contains the last finalized transcript. The complete end-user utterance is determined by concatenating the finalized transcript values received for the series of results. In the following example, single utterance is enabled. In the case where single utterance is not enabled, result 7 would not occur. ``` Num | transcript | message_type | is_final --- | ----------------------- | ----------------------- | -------- 1 | \"tube\" | TRANSCRIPT | false 2 | \"to be a\" | TRANSCRIPT | false 3 | \"to be\" | TRANSCRIPT | false 4 | \"to be or not to be\" | TRANSCRIPT | true 5 | \"that's\" | TRANSCRIPT | false 6 | \"that is | TRANSCRIPT | false 7 | unset | END_OF_SINGLE_UTTERANCE | unset 8 | \" that is the question\" | TRANSCRIPT | true ``` Concatenating the finalized transcripts with `is_final` set to true, the complete utterance becomes \"to be or not to be that is the question\".",
+"id": "GoogleCloudDialogflowV2StreamingRecognitionResult",
+"properties": {
+"confidence": {
+"description": "The Speech confidence between 0.0 and 1.0 for the current portion of audio. A higher number indicates an estimated greater likelihood that the recognized words are correct. The default of 0.0 is a sentinel value indicating that confidence was not set. This field is typically only provided if `is_final` is true and you should not rely on it being accurate or even set.",
+"format": "float",
+"type": "number"
+},
+"isFinal": {
+"description": "If `false`, the `StreamingRecognitionResult` represents an interim result that may change. If `true`, the recognizer will not return any further hypotheses about this piece of the audio. May only be populated for `message_type` = `TRANSCRIPT`.",
+"type": "boolean"
+},
+"languageCode": {
+"description": "Detected language code for the transcript.",
+"type": "string"
+},
+"messageType": {
+"description": "Type of the result message.",
+"enum": [
+"MESSAGE_TYPE_UNSPECIFIED",
+"TRANSCRIPT",
+"END_OF_SINGLE_UTTERANCE"
+],
+"enumDescriptions": [
+"Not specified. Should never be used.",
+"Message contains a (possibly partial) transcript.",
+"This event indicates that the server has detected the end of the user's speech utterance and expects no additional inputs. Therefore, the server will not process additional audio (although it may subsequently return additional results). The client should stop sending additional audio data, half-close the gRPC connection, and wait for any additional results until the server closes the gRPC connection. This message is only sent if `single_utterance` was set to `true`, and is not used otherwise."
+],
+"type": "string"
+},
+"speechEndOffset": {
+"description": "Time offset of the end of this Speech recognition result relative to the beginning of the audio. Only populated for `message_type` = `TRANSCRIPT`.",
+"format": "google-duration",
+"type": "string"
+},
+"speechWordInfo": {
+"description": "Word-specific information for the words recognized by Speech in transcript. Populated if and only if `message_type` = `TRANSCRIPT` and [InputAudioConfig.enable_word_info] is set.",
+"items": {
+"$ref": "GoogleCloudDialogflowV2SpeechWordInfo"
+},
+"type": "array"
+},
+"transcript": {
+"description": "Transcript text representing the words that the user spoke. Populated if and only if `message_type` = `TRANSCRIPT`.",
+"type": "string"
+}
+},
+"type": "object"
+},
 "GoogleCloudDialogflowV2SuggestArticlesResponse": {
 "description": "The response message for Participants.SuggestArticles.",
 "id": "GoogleCloudDialogflowV2SuggestArticlesResponse",
@@ -15110,6 +15192,10 @@ true
 "$ref": "GoogleCloudDialogflowV2beta1Message",
 "description": "Payload of NEW_MESSAGE event."
 },
+"newRecognitionResultPayload": {
+"$ref": "GoogleCloudDialogflowV2beta1StreamingRecognitionResult",
+"description": "Payload of NEW_RECOGNITION_RESULT event."
+},
 "type": {
 "description": "Required. The type of the event that this notification refers to.",
 "enum": [
@@ -15118,6 +15204,7 @@ true
 "CONVERSATION_FINISHED",
 "HUMAN_INTERVENTION_NEEDED",
 "NEW_MESSAGE",
+"NEW_RECOGNITION_RESULT",
 "UNRECOVERABLE_ERROR"
 ],
 "enumDescriptions": [
@@ -15126,6 +15213,7 @@ true
 "An existing conversation has closed. This is fired when a telephone call is terminated, or a conversation is closed via the API.",
 "An existing conversation has received notification from Dialogflow that human intervention is required.",
 "An existing conversation has received a new message, either from API or telephony. It is configured in ConversationProfile.new_message_event_notification_config",
+"An existing conversation has received a new speech recognition result. This is mainly for delivering intermediate transcripts. The notification is configured in ConversationProfile.new_recognition_event_notification_config.",
 "Unrecoverable error during a telephone call. In general non-recoverable errors only occur if something was misconfigured in the ConversationProfile corresponding to the call. After a non-recoverable error, Dialogflow may stop responding. We don't fire this event: * in an API call because we can directly return the error, or, * when we can recover from an error."
 ],
 "type": "string"
@@ -17273,6 +17361,95 @@ true
 },
 "type": "object"
 },
+"GoogleCloudDialogflowV2beta1SpeechWordInfo": {
+"description": "Information for a word recognized by the speech recognizer.",
+"id": "GoogleCloudDialogflowV2beta1SpeechWordInfo",
+"properties": {
+"confidence": {
+"description": "The Speech confidence between 0.0 and 1.0 for this word. A higher number indicates an estimated greater likelihood that the recognized word is correct. The default of 0.0 is a sentinel value indicating that confidence was not set. This field is not guaranteed to be fully stable over time for the same audio input. Users should also not rely on it to always be provided.",
+"format": "float",
+"type": "number"
+},
+"endOffset": {
+"description": "Time offset relative to the beginning of the audio that corresponds to the end of the spoken word. This is an experimental feature and the accuracy of the time offset can vary.",
+"format": "google-duration",
+"type": "string"
+},
+"startOffset": {
+"description": "Time offset relative to the beginning of the audio that corresponds to the start of the spoken word. This is an experimental feature and the accuracy of the time offset can vary.",
+"format": "google-duration",
+"type": "string"
+},
+"word": {
+"description": "The word this info is for.",
+"type": "string"
+}
+},
+"type": "object"
+},
+"GoogleCloudDialogflowV2beta1StreamingRecognitionResult": {
+"description": "Contains a speech recognition result corresponding to a portion of the audio that is currently being processed or an indication that this is the end of the single requested utterance. While end-user audio is being processed, Dialogflow sends a series of results. Each result may contain a `transcript` value. A transcript represents a portion of the utterance. While the recognizer is processing audio, transcript values may be interim values or finalized values. Once a transcript is finalized, the `is_final` value is set to true and processing continues for the next transcript. If `StreamingDetectIntentRequest.query_input.audio_config.single_utterance` was true, and the recognizer has completed processing audio, the `message_type` value is set to `END_OF_SINGLE_UTTERANCE and the following (last) result contains the last finalized transcript. The complete end-user utterance is determined by concatenating the finalized transcript values received for the series of results. In the following example, single utterance is enabled. In the case where single utterance is not enabled, result 7 would not occur. ``` Num | transcript | message_type | is_final --- | ----------------------- | ----------------------- | -------- 1 | \"tube\" | TRANSCRIPT | false 2 | \"to be a\" | TRANSCRIPT | false 3 | \"to be\" | TRANSCRIPT | false 4 | \"to be or not to be\" | TRANSCRIPT | true 5 | \"that's\" | TRANSCRIPT | false 6 | \"that is | TRANSCRIPT | false 7 | unset | END_OF_SINGLE_UTTERANCE | unset 8 | \" that is the question\" | TRANSCRIPT | true ``` Concatenating the finalized transcripts with `is_final` set to true, the complete utterance becomes \"to be or not to be that is the question\".",
+"id": "GoogleCloudDialogflowV2beta1StreamingRecognitionResult",
+"properties": {
+"confidence": {
+"description": "The Speech confidence between 0.0 and 1.0 for the current portion of audio. A higher number indicates an estimated greater likelihood that the recognized words are correct. The default of 0.0 is a sentinel value indicating that confidence was not set. This field is typically only provided if `is_final` is true and you should not rely on it being accurate or even set.",
+"format": "float",
+"type": "number"
+},
+"dtmfDigits": {
+"$ref": "GoogleCloudDialogflowV2beta1TelephonyDtmfEvents",
+"description": "DTMF digits. Populated if and only if `message_type` = `DTMF_DIGITS`."
+},
+"isFinal": {
+"description": "If `false`, the `StreamingRecognitionResult` represents an interim result that may change. If `true`, the recognizer will not return any further hypotheses about this piece of the audio. May only be populated for `message_type` = `TRANSCRIPT`.",
+"type": "boolean"
+},
+"languageCode": {
+"description": "Detected language code for the transcript.",
+"type": "string"
+},
+"messageType": {
+"description": "Type of the result message.",
+"enum": [
+"MESSAGE_TYPE_UNSPECIFIED",
+"TRANSCRIPT",
+"DTMF_DIGITS",
+"END_OF_SINGLE_UTTERANCE",
+"PARTIAL_DTMF_DIGITS"
+],
+"enumDescriptions": [
+"Not specified. Should never be used.",
+"Message contains a (possibly partial) transcript.",
+"Message contains DTMF digits.",
+"This event indicates that the server has detected the end of the user's speech utterance and expects no additional speech. Therefore, the server will not process additional audio (although it may subsequently return additional results). The client should stop sending additional audio data, half-close the gRPC connection, and wait for any additional results until the server closes the gRPC connection. This message is only sent if `single_utterance` was set to `true`, and is not used otherwise.",
+"Message contains DTMF digits. Before a message with DTMF_DIGITS is sent, a message with PARTIAL_DTMF_DIGITS may be sent with DTMF digits collected up to the time of sending, which represents an intermediate result."
+],
+"type": "string"
+},
+"speechEndOffset": {
+"description": "Time offset of the end of this Speech recognition result relative to the beginning of the audio. Only populated for `message_type` = `TRANSCRIPT`.",
+"format": "google-duration",
+"type": "string"
+},
+"speechWordInfo": {
+"description": "Word-specific information for the words recognized by Speech in transcript. Populated if and only if `message_type` = `TRANSCRIPT` and [InputAudioConfig.enable_word_info] is set.",
+"items": {
+"$ref": "GoogleCloudDialogflowV2beta1SpeechWordInfo"
+},
+"type": "array"
+},
+"stability": {
+"description": "An estimate of the likelihood that the speech recognizer will not change its guess about this interim recognition result: * If the value is unspecified or 0.0, Dialogflow didn't compute the stability. In particular, Dialogflow will only provide stability for `TRANSCRIPT` results with `is_final = false`. * Otherwise, the value is in (0.0, 1.0] where 0.0 means completely unstable and 1.0 means completely stable.",
+"format": "float",
+"type": "number"
+},
+"transcript": {
+"description": "Transcript text representing the words that the user spoke. Populated if and only if `message_type` = `TRANSCRIPT`.",
+"type": "string"
+}
+},
+"type": "object"
+},
 "GoogleCloudDialogflowV2beta1SuggestArticlesResponse": {
 "description": "The response message for Participants.SuggestArticles.",
 "id": "GoogleCloudDialogflowV2beta1SuggestArticlesResponse",
@@ -17421,6 +17598,58 @@ true
 },
 "type": "object"
 },
+"GoogleCloudDialogflowV2beta1TelephonyDtmfEvents": {
+"description": "A wrapper of repeated TelephonyDtmf digits.",
+"id": "GoogleCloudDialogflowV2beta1TelephonyDtmfEvents",
+"properties": {
+"dtmfEvents": {
+"description": "A sequence of TelephonyDtmf digits.",
+"items": {
+"enum": [
+"TELEPHONY_DTMF_UNSPECIFIED",
+"DTMF_ONE",
+"DTMF_TWO",
+"DTMF_THREE",
+"DTMF_FOUR",
+"DTMF_FIVE",
+"DTMF_SIX",
+"DTMF_SEVEN",
+"DTMF_EIGHT",
+"DTMF_NINE",
+"DTMF_ZERO",
+"DTMF_A",
+"DTMF_B",
+"DTMF_C",
+"DTMF_D",
+"DTMF_STAR",
+"DTMF_POUND"
+],
+"enumDescriptions": [
+"Not specified. This value may be used to indicate an absent digit.",
+"Number: '1'.",
+"Number: '2'.",
+"Number: '3'.",
+"Number: '4'.",
+"Number: '5'.",
+"Number: '6'.",
+"Number: '7'.",
+"Number: '8'.",
+"Number: '9'.",
+"Number: '0'.",
+"Letter: 'A'.",
+"Letter: 'B'.",
+"Letter: 'C'.",
+"Letter: 'D'.",
+"Asterisk/star: '*'.",
+"Pound/diamond/hash/square/gate/octothorpe: '#'."
+],
+"type": "string"
+},
+"type": "array"
+}
+},
+"type": "object"
+},
 "GoogleCloudDialogflowV2beta1WebhookRequest": {
 "description": "The request message for a webhook call.",
 "id": "GoogleCloudDialogflowV2beta1WebhookRequest",

googleapiclient/discovery_cache/documents/dialogflow.v3beta1.json

@@ -5272,7 +5272,7 @@
 }
 }
 },
-"revision": "20241212",
+"revision": "20241216",
 "rootUrl": "https://dialogflow.googleapis.com/",
 "schemas": {
 "GoogleCloudDialogflowCxV3AdvancedSettings": {
@@ -8468,6 +8468,13 @@
 "responseUtterances": {
 "description": "The output text or the transcript of the output audio in the responses. If multiple output messages are returned, they will be concatenated into one.",
 "type": "string"
+},
+"stepMetrics": {
+"description": "Metrics associated with different processing steps. Names and number of steps depend on the request and can change without a notice.",
+"items": {
+"$ref": "GoogleCloudDialogflowCxV3beta1ConversationInteractionStepMetrics"
+},
+"type": "array"
 }
 },
 "type": "object"
@@ -8488,6 +8495,22 @@
 },
 "type": "object"
 },
+"GoogleCloudDialogflowCxV3beta1ConversationInteractionStepMetrics": {
+"description": "Metrics of each processing step.",
+"id": "GoogleCloudDialogflowCxV3beta1ConversationInteractionStepMetrics",
+"properties": {
+"latency": {
+"description": "Processing latency of the step.",
+"format": "google-duration",
+"type": "string"
+},
+"name": {
+"description": "Name of the request processing step.",
+"type": "string"
+}
+},
+"type": "object"
+},
 "GoogleCloudDialogflowCxV3beta1ConversationMetrics": {
 "description": "Represents metrics for the conversation.",
 "id": "GoogleCloudDialogflowCxV3beta1ConversationMetrics",
@@ -15119,6 +15142,10 @@ false
 "$ref": "GoogleCloudDialogflowV2Message",
 "description": "Payload of NEW_MESSAGE event."
 },
+"newRecognitionResultPayload": {
+"$ref": "GoogleCloudDialogflowV2StreamingRecognitionResult",
+"description": "Payload of NEW_RECOGNITION_RESULT event."
+},
 "type": {
 "description": "The type of the event that this notification refers to.",
 "enum": [
@@ -15127,6 +15154,7 @@ false
 "CONVERSATION_FINISHED",
 "HUMAN_INTERVENTION_NEEDED",
 "NEW_MESSAGE",
+"NEW_RECOGNITION_RESULT",
 "UNRECOVERABLE_ERROR"
 ],
 "enumDescriptions": [
@@ -15135,6 +15163,7 @@ false
 "An existing conversation has closed. This is fired when a telephone call is terminated, or a conversation is closed via the API.",
 "An existing conversation has received notification from Dialogflow that human intervention is required.",
 "An existing conversation has received a new message, either from API or telephony. It is configured in ConversationProfile.new_message_event_notification_config",
+"An existing conversation has received a new speech recognition result. This is mainly for delivering intermediate transcripts. The notification is configured in ConversationProfile.new_recognition_event_notification_config.",
 "Unrecoverable error during a telephone call. In general non-recoverable errors only occur if something was misconfigured in the ConversationProfile corresponding to the call. After a non-recoverable error, Dialogflow may stop responding. We don't fire this event: * in an API call because we can directly return the error, or, * when we can recover from an error."
 ],
 "type": "string"
@@ -17034,6 +17063,82 @@ true
 },
 "type": "object"
 },
+"GoogleCloudDialogflowV2SpeechWordInfo": {
+"description": "Information for a word recognized by the speech recognizer.",
+"id": "GoogleCloudDialogflowV2SpeechWordInfo",
+"properties": {
+"confidence": {
+"description": "The Speech confidence between 0.0 and 1.0 for this word. A higher number indicates an estimated greater likelihood that the recognized word is correct. The default of 0.0 is a sentinel value indicating that confidence was not set. This field is not guaranteed to be fully stable over time for the same audio input. Users should also not rely on it to always be provided.",
+"format": "float",
+"type": "number"
+},
+"endOffset": {
+"description": "Time offset relative to the beginning of the audio that corresponds to the end of the spoken word. This is an experimental feature and the accuracy of the time offset can vary.",
+"format": "google-duration",
+"type": "string"
+},
+"startOffset": {
+"description": "Time offset relative to the beginning of the audio that corresponds to the start of the spoken word. This is an experimental feature and the accuracy of the time offset can vary.",
+"format": "google-duration",
+"type": "string"
+},
+"word": {
+"description": "The word this info is for.",
+"type": "string"
+}
+},
+"type": "object"
+},
+"GoogleCloudDialogflowV2StreamingRecognitionResult": {
+"description": "Contains a speech recognition result corresponding to a portion of the audio that is currently being processed or an indication that this is the end of the single requested utterance. While end-user audio is being processed, Dialogflow sends a series of results. Each result may contain a `transcript` value. A transcript represents a portion of the utterance. While the recognizer is processing audio, transcript values may be interim values or finalized values. Once a transcript is finalized, the `is_final` value is set to true and processing continues for the next transcript. If `StreamingDetectIntentRequest.query_input.audio_config.single_utterance` was true, and the recognizer has completed processing audio, the `message_type` value is set to `END_OF_SINGLE_UTTERANCE and the following (last) result contains the last finalized transcript. The complete end-user utterance is determined by concatenating the finalized transcript values received for the series of results. In the following example, single utterance is enabled. In the case where single utterance is not enabled, result 7 would not occur. ``` Num | transcript | message_type | is_final --- | ----------------------- | ----------------------- | -------- 1 | \"tube\" | TRANSCRIPT | false 2 | \"to be a\" | TRANSCRIPT | false 3 | \"to be\" | TRANSCRIPT | false 4 | \"to be or not to be\" | TRANSCRIPT | true 5 | \"that's\" | TRANSCRIPT | false 6 | \"that is | TRANSCRIPT | false 7 | unset | END_OF_SINGLE_UTTERANCE | unset 8 | \" that is the question\" | TRANSCRIPT | true ``` Concatenating the finalized transcripts with `is_final` set to true, the complete utterance becomes \"to be or not to be that is the question\".",
+"id": "GoogleCloudDialogflowV2StreamingRecognitionResult",
+"properties": {
+"confidence": {
+"description": "The Speech confidence between 0.0 and 1.0 for the current portion of audio. A higher number indicates an estimated greater likelihood that the recognized words are correct. The default of 0.0 is a sentinel value indicating that confidence was not set. This field is typically only provided if `is_final` is true and you should not rely on it being accurate or even set.",
+"format": "float",
+"type": "number"
+},
+"isFinal": {
+"description": "If `false`, the `StreamingRecognitionResult` represents an interim result that may change. If `true`, the recognizer will not return any further hypotheses about this piece of the audio. May only be populated for `message_type` = `TRANSCRIPT`.",
+"type": "boolean"
+},
+"languageCode": {
+"description": "Detected language code for the transcript.",
+"type": "string"
+},
+"messageType": {
+"description": "Type of the result message.",
+"enum": [
+"MESSAGE_TYPE_UNSPECIFIED",
+"TRANSCRIPT",
+"END_OF_SINGLE_UTTERANCE"
+],
+"enumDescriptions": [
+"Not specified. Should never be used.",
+"Message contains a (possibly partial) transcript.",
+"This event indicates that the server has detected the end of the user's speech utterance and expects no additional inputs. Therefore, the server will not process additional audio (although it may subsequently return additional results). The client should stop sending additional audio data, half-close the gRPC connection, and wait for any additional results until the server closes the gRPC connection. This message is only sent if `single_utterance` was set to `true`, and is not used otherwise."
+],
+"type": "string"
+},
+"speechEndOffset": {
+"description": "Time offset of the end of this Speech recognition result relative to the beginning of the audio. Only populated for `message_type` = `TRANSCRIPT`.",
+"format": "google-duration",
+"type": "string"
+},
+"speechWordInfo": {
+"description": "Word-specific information for the words recognized by Speech in transcript. Populated if and only if `message_type` = `TRANSCRIPT` and [InputAudioConfig.enable_word_info] is set.",
+"items": {
+"$ref": "GoogleCloudDialogflowV2SpeechWordInfo"
+},
+"type": "array"
+},
+"transcript": {
+"description": "Transcript text representing the words that the user spoke. Populated if and only if `message_type` = `TRANSCRIPT`.",
+"type": "string"
+}
+},
+"type": "object"
+},
 "GoogleCloudDialogflowV2SuggestArticlesResponse": {
 "description": "The response message for Participants.SuggestArticles.",
 "id": "GoogleCloudDialogflowV2SuggestArticlesResponse",
@@ -17415,6 +17520,10 @@ true
 "$ref": "GoogleCloudDialogflowV2beta1Message",
 "description": "Payload of NEW_MESSAGE event."
 },
+"newRecognitionResultPayload": {
+"$ref": "GoogleCloudDialogflowV2beta1StreamingRecognitionResult",
+"description": "Payload of NEW_RECOGNITION_RESULT event."
+},
 "type": {
 "description": "Required. The type of the event that this notification refers to.",
 "enum": [
@@ -17423,6 +17532,7 @@ true
 "CONVERSATION_FINISHED",
 "HUMAN_INTERVENTION_NEEDED",
 "NEW_MESSAGE",
+"NEW_RECOGNITION_RESULT",
 "UNRECOVERABLE_ERROR"
 ],
 "enumDescriptions": [
@@ -17431,6 +17541,7 @@ true
 "An existing conversation has closed. This is fired when a telephone call is terminated, or a conversation is closed via the API.",
 "An existing conversation has received notification from Dialogflow that human intervention is required.",
 "An existing conversation has received a new message, either from API or telephony. It is configured in ConversationProfile.new_message_event_notification_config",
+"An existing conversation has received a new speech recognition result. This is mainly for delivering intermediate transcripts. The notification is configured in ConversationProfile.new_recognition_event_notification_config.",
 "Unrecoverable error during a telephone call. In general non-recoverable errors only occur if something was misconfigured in the ConversationProfile corresponding to the call. After a non-recoverable error, Dialogflow may stop responding. We don't fire this event: * in an API call because we can directly return the error, or, * when we can recover from an error."
 ],
 "type": "string"
@@ -19578,6 +19689,95 @@ true
 },
 "type": "object"
 },
+"GoogleCloudDialogflowV2beta1SpeechWordInfo": {
+"description": "Information for a word recognized by the speech recognizer.",
+"id": "GoogleCloudDialogflowV2beta1SpeechWordInfo",
+"properties": {
+"confidence": {
+"description": "The Speech confidence between 0.0 and 1.0 for this word. A higher number indicates an estimated greater likelihood that the recognized word is correct. The default of 0.0 is a sentinel value indicating that confidence was not set. This field is not guaranteed to be fully stable over time for the same audio input. Users should also not rely on it to always be provided.",
+"format": "float",
+"type": "number"
+},
+"endOffset": {
+"description": "Time offset relative to the beginning of the audio that corresponds to the end of the spoken word. This is an experimental feature and the accuracy of the time offset can vary.",
+"format": "google-duration",
+"type": "string"
+},
+"startOffset": {
+"description": "Time offset relative to the beginning of the audio that corresponds to the start of the spoken word. This is an experimental feature and the accuracy of the time offset can vary.",
+"format": "google-duration",
+"type": "string"
+},
+"word": {
+"description": "The word this info is for.",
+"type": "string"
+}
+},
+"type": "object"
+},
+"GoogleCloudDialogflowV2beta1StreamingRecognitionResult": {
+"description": "Contains a speech recognition result corresponding to a portion of the audio that is currently being processed or an indication that this is the end of the single requested utterance. While end-user audio is being processed, Dialogflow sends a series of results. Each result may contain a `transcript` value. A transcript represents a portion of the utterance. While the recognizer is processing audio, transcript values may be interim values or finalized values. Once a transcript is finalized, the `is_final` value is set to true and processing continues for the next transcript. If `StreamingDetectIntentRequest.query_input.audio_config.single_utterance` was true, and the recognizer has completed processing audio, the `message_type` value is set to `END_OF_SINGLE_UTTERANCE and the following (last) result contains the last finalized transcript. The complete end-user utterance is determined by concatenating the finalized transcript values received for the series of results. In the following example, single utterance is enabled. In the case where single utterance is not enabled, result 7 would not occur. ``` Num | transcript | message_type | is_final --- | ----------------------- | ----------------------- | -------- 1 | \"tube\" | TRANSCRIPT | false 2 | \"to be a\" | TRANSCRIPT | false 3 | \"to be\" | TRANSCRIPT | false 4 | \"to be or not to be\" | TRANSCRIPT | true 5 | \"that's\" | TRANSCRIPT | false 6 | \"that is | TRANSCRIPT | false 7 | unset | END_OF_SINGLE_UTTERANCE | unset 8 | \" that is the question\" | TRANSCRIPT | true ``` Concatenating the finalized transcripts with `is_final` set to true, the complete utterance becomes \"to be or not to be that is the question\".",
+"id": "GoogleCloudDialogflowV2beta1StreamingRecognitionResult",
+"properties": {
+"confidence": {
+"description": "The Speech confidence between 0.0 and 1.0 for the current portion of audio. A higher number indicates an estimated greater likelihood that the recognized words are correct. The default of 0.0 is a sentinel value indicating that confidence was not set. This field is typically only provided if `is_final` is true and you should not rely on it being accurate or even set.",
+"format": "float",
+"type": "number"
+},
+"dtmfDigits": {
+"$ref": "GoogleCloudDialogflowV2beta1TelephonyDtmfEvents",
+"description": "DTMF digits. Populated if and only if `message_type` = `DTMF_DIGITS`."
+},
+"isFinal": {
+"description": "If `false`, the `StreamingRecognitionResult` represents an interim result that may change. If `true`, the recognizer will not return any further hypotheses about this piece of the audio. May only be populated for `message_type` = `TRANSCRIPT`.",
+"type": "boolean"
+},
+"languageCode": {
+"description": "Detected language code for the transcript.",
+"type": "string"
+},
+"messageType": {
+"description": "Type of the result message.",
+"enum": [
+"MESSAGE_TYPE_UNSPECIFIED",
+"TRANSCRIPT",
+"DTMF_DIGITS",
+"END_OF_SINGLE_UTTERANCE",
+"PARTIAL_DTMF_DIGITS"
+],
+"enumDescriptions": [
+"Not specified. Should never be used.",
+"Message contains a (possibly partial) transcript.",
+"Message contains DTMF digits.",
+"This event indicates that the server has detected the end of the user's speech utterance and expects no additional speech. Therefore, the server will not process additional audio (although it may subsequently return additional results). The client should stop sending additional audio data, half-close the gRPC connection, and wait for any additional results until the server closes the gRPC connection. This message is only sent if `single_utterance` was set to `true`, and is not used otherwise.",
+"Message contains DTMF digits. Before a message with DTMF_DIGITS is sent, a message with PARTIAL_DTMF_DIGITS may be sent with DTMF digits collected up to the time of sending, which represents an intermediate result."
+],
+"type": "string"
+},
+"speechEndOffset": {
+"description": "Time offset of the end of this Speech recognition result relative to the beginning of the audio. Only populated for `message_type` = `TRANSCRIPT`.",
+"format": "google-duration",
+"type": "string"
+},
+"speechWordInfo": {
+"description": "Word-specific information for the words recognized by Speech in transcript. Populated if and only if `message_type` = `TRANSCRIPT` and [InputAudioConfig.enable_word_info] is set.",
+"items": {
+"$ref": "GoogleCloudDialogflowV2beta1SpeechWordInfo"
+},
+"type": "array"
+},
+"stability": {
+"description": "An estimate of the likelihood that the speech recognizer will not change its guess about this interim recognition result: * If the value is unspecified or 0.0, Dialogflow didn't compute the stability. In particular, Dialogflow will only provide stability for `TRANSCRIPT` results with `is_final = false`. * Otherwise, the value is in (0.0, 1.0] where 0.0 means completely unstable and 1.0 means completely stable.",
+"format": "float",
+"type": "number"
+},
+"transcript": {
+"description": "Transcript text representing the words that the user spoke. Populated if and only if `message_type` = `TRANSCRIPT`.",
+"type": "string"
+}
+},
+"type": "object"
+},
 "GoogleCloudDialogflowV2beta1SuggestArticlesResponse": {
 "description": "The response message for Participants.SuggestArticles.",
 "id": "GoogleCloudDialogflowV2beta1SuggestArticlesResponse",
@@ -19726,6 +19926,58 @@ true
 },
 "type": "object"
 },
+"GoogleCloudDialogflowV2beta1TelephonyDtmfEvents": {
+"description": "A wrapper of repeated TelephonyDtmf digits.",
+"id": "GoogleCloudDialogflowV2beta1TelephonyDtmfEvents",
+"properties": {
+"dtmfEvents": {
+"description": "A sequence of TelephonyDtmf digits.",
+"items": {
+"enum": [
+"TELEPHONY_DTMF_UNSPECIFIED",
+"DTMF_ONE",
+"DTMF_TWO",
+"DTMF_THREE",
+"DTMF_FOUR",
+"DTMF_FIVE",
+"DTMF_SIX",
+"DTMF_SEVEN",
+"DTMF_EIGHT",
+"DTMF_NINE",
+"DTMF_ZERO",
+"DTMF_A",
+"DTMF_B",
+"DTMF_C",
+"DTMF_D",
+"DTMF_STAR",
+"DTMF_POUND"
+],
+"enumDescriptions": [
+"Not specified. This value may be used to indicate an absent digit.",
+"Number: '1'.",
+"Number: '2'.",
+"Number: '3'.",
+"Number: '4'.",
+"Number: '5'.",
+"Number: '6'.",
+"Number: '7'.",
+"Number: '8'.",
+"Number: '9'.",
+"Number: '0'.",
+"Letter: 'A'.",
+"Letter: 'B'.",
+"Letter: 'C'.",
+"Letter: 'D'.",
+"Asterisk/star: '*'.",
+"Pound/diamond/hash/square/gate/octothorpe: '#'."
+],
+"type": "string"
+},
+"type": "array"
+}
+},
+"type": "object"
+},
 "GoogleCloudDialogflowV2beta1WebhookRequest": {
 "description": "The request message for a webhook call.",
 "id": "GoogleCloudDialogflowV2beta1WebhookRequest",