OptionalconfidenceConfidence score for the transcription (0-1). Higher values indicate more accurate transcription.
OptionalemotionEmotion classification from mood analysis.
OptionalengagementEngagement level from mood analysis (0-1).
Unique identifier for this entry.
Typically ${speaker}-${timestamp}.
OptionallanguageISO language code (e.g., 'en', 'es', 'fr').
OptionalreceivedWhen the transcription was received by the client.
OptionalsentimentSentiment classification from mood analysis.
User ID of the speaker.
OptionalspeakerDisplay name of the speaker (if available).
The transcribed text content.
When the transcription was generated.
A single transcription entry from speech-to-text.
Remarks
Each entry represents a segment of speech transcribed in real-time. Entries are typically grouped by speaker and time window for display.