Virtual Agents Transcript and Call Summary

Content.

Call Insight Type.

Signed seconds of the span of time. Must be from -315,576,000,000 to +315,576,000,000 inclusive. Note: these bounds are computed from: 60 sec/min * 60 min/hr * 24 hr/day * 365.25 days/year * 10000 years.

Signed fractions of a second at nanosecond resolution of the span of time. Durations less than one second are represented with a 0 seconds field and a positive or negative nanos field. For durations of one second or more, a non-zero value for the nanos field must be of the same sign as the seconds field. Must be from -999,999,999 to +999,999,999 inclusive.

Call Transfer Metadata.

Event Type.

Optional: To be used for the custom event.

Optional: Map to pass the custom params.

Required. Conversation ID for which insights are needed. The subscription will start listening to any insights for this conversation across multiple legs( IVR, Caller, Agent) and services (Transcription, Agent Assist).

Required.Control Hub OrgID for the org, this conversation belongs to. The Access token should have authorization for this Org.

Is historical transcripts from start of the conversation required? Default: false.

Is virtual agent from start of the conversation required? Default: false.

Required. AgentDetails from where the call is initiated.

Sets the message id for the request , this uniquely identifies each request .

Org Identifier (control hub) for which the insights need to be delivered.

Identifier for the Conversation. Equivalent to Call ID, CallGUID etc.

Identifier for the individual leg, based on the party. GUID.

Identifier for a given utterance. The same utterance ID will be published for the transcript utterance and the insights generated from it.

Role specifying IVR, Caller or Agent.

Type of insight : ASR, Agent Assist etc.

Service Provider who produced this insight.

Epoch Timestamp when this insight record was created/published. This field is always available, can be used for sorting messages by time.

Start time and end time corresponds to the speech interval to which this insight belongs. Epoch Timestamp. These are optional fields, not always available.

Whether the insight is final or intermediate. Intermediate results will be overridden by the final result that follows them.

message id.

Content of the insight. This will vary based on the type of insight.

Required. Conversation ID (in combination with the messageId, if provided)for which insights are needed. The subscription will start listening to any insights for this conversation (along with messageId if provided) across multiple legs( IVR, Caller, Agent) and services (Transcription, Agent Assist).

Optional. if messageId is provided then the insights are fetched with the combination of conversationId. The subscription will start listening to any insights for this messageID along with the conversationId field across multiple legs( IVR, Caller, Agent) and services (Transcription, Agent Assist).

Required.Control Hub OrgID for the org, this conversation belongs to. The Access token should have authorization for this Org.

Required. Conversation ID (in combination with the messageId, if provided)for which insights are needed. The subscription will start listening to any insights for this conversation (along with messageId if provided) across multiple legs( IVR, Caller, Agent) and services (Transcription, Agent Assist).

Optional. if messageId is provided then the insights are fetched with the combination of conversationId. The subscription will start listening to any insights for this messageID along with the conversationId field across multiple legs( IVR, Caller, Agent) and services (Transcription, Agent Assist).

Required.Control Hub OrgID for the org, this conversation belongs to. The Access token should have authorization for this Org.

Start time and end time corresponds to the speech interval to which this insight belongs. Epoch Timestamp. These are optional fields, not always available.

Service Provider who produced this insight.

Content of the insight. This will vary based on the type of insight.

Name of the Intent.

Display name of the Intent.

Parameters of an Intent, filled / not filled.

Match Confidence.

Response in text. This will be used for Virtual Agent Transcript.

Intent detected from the last utterance.

Sent when the call is transferred to Agent.

Call Ended.

user input uttered by caller.

Exit Event to return the control back to the calling flow.

Placeholder for any other types. Not returned unless stated.

For Service Type = TRANSCRIPTION.

For Service Type = VIRTUAL_AGENT.

For Service Type = CALL_INSIGHTS.

Output only. Transcript text representing the words that the user spoke.

Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative of a non-streaming result or, of a streaming result where is_final=true. Not yet supported.

Output only. A list of word-specific information for each recognized word. Note: When enable_speaker_diarization is true, you will see all the words from the beginning of the audio.

Output only. May contain one or more recognition hypotheses (up to the maximum specified in max_alternatives). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.

Output only. If false, this StreamingRecognitionResult represents an interim result that may change. If true, this is the final time the speech service will return this particular StreamingRecognitionResult, the recognizer will not return any further hypotheses for this portion of the transcript and corresponding audio.

Output only. Time offset of the end of this result relative to the beginning of the audio.

For multi-channel audio, this is the channel number corresponding to the recognized result for the audio from that channel. For audio_channel_count = N, its output values can range from '1' to 'N'.

Output only. The BCP-47 language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.

Whether or not recording offsets have been applied to the word alignment values. Otherwise the word alignment start and end times are only relative within the utterance.

Zero or more integers representing the speaker ID of this result. This is usually derived from the speaker integers that are passed in the streaming request.

The unix time in milliseconds which was received from the client for the StreamingRecognizeRequest that was last used to complete this utterance.

message type.

Event Based on user utterances.

Output only. Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if enable_word_time_offsets=true and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.

Output only. Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if enable_word_time_offsets=true and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.

Output only. The word corresponding to this set of information.

Triggers when user utter the first utterance in Voice Input mode or First DTMF is pressed in DTMF Input mode. This event to be used to BargeIn the prompt based on prompt barge-in flag. The event will be sent only if the current prompt being played is bargein enabled or prompt playing is complete.

Sent when user utterance Voice / DTMF is complete.

Sent when utterance did not match any of the accepted input.

Sent when no audio received with in the expected timeframe.

Role - Undefined.

Role - Caller.