UtteranceEvent¶
Structure Class¶
UtteranceEvent
dataclass
¶
Contains set of transcription results from one or more audio segments, along with additional information about the parameters included in your request. For example, channel definitions, partial result stabilization, sentiment, and issue detection.
Attributes¶
begin_offset_millis
class-attribute
instance-attribute
¶
begin_offset_millis: int | None = None
The time, in milliseconds, from the beginning of the audio stream to the
start of the UtteranceEvent.
end_offset_millis
class-attribute
instance-attribute
¶
end_offset_millis: int | None = None
The time, in milliseconds, from the beginning of the audio stream to the
start of the UtteranceEvent.
entities
class-attribute
instance-attribute
¶
entities: list[CallAnalyticsEntity] | None = None
Contains entities identified as personally identifiable information (PII) in your transcription output.
is_partial
class-attribute
instance-attribute
¶
is_partial: bool = False
Indicates whether the segment in the UtteranceEvent is complete
(FALSE) or partial (TRUE).
issues_detected
class-attribute
instance-attribute
¶
issues_detected: list[IssueDetected] | None = None
Provides the issue that was detected in the specified segment.
items
class-attribute
instance-attribute
¶
items: list[CallAnalyticsItem] | None = None
Contains words, phrases, or punctuation marks that are associated with
the specified UtteranceEvent.
language_code
class-attribute
instance-attribute
¶
language_code: CallAnalyticsLanguageCode | None = None
The language code that represents the language spoken in your audio stream.
language_identification
class-attribute
instance-attribute
¶
language_identification: list[CallAnalyticsLanguageWithScore] | None = None
The language code of the dominant language identified in your stream.
participant_role
class-attribute
instance-attribute
¶
participant_role: ParticipantRole | None = None
Provides the role of the speaker for each audio channel, either
CUSTOMER or AGENT.
sentiment
class-attribute
instance-attribute
¶
sentiment: Sentiment | None = None
Provides the sentiment that was detected in the specified segment.
transcript
class-attribute
instance-attribute
¶
transcript: str | None = None
Contains transcribed text.
utterance_id
class-attribute
instance-attribute
¶
utterance_id: str | None = None
The unique identifier that is associated with the specified
UtteranceEvent.