Live Digest
Monitoring
Live Digest
Generate periodic narrative summaries via SSE streaming
POST
Live Digest
Starts a summary-oriented monitoring job that samples the stream and emits narrative summaries.
Use this when you need trend-level understanding over time, not binary trigger detection.
Delivery Mode Selection
POST /live-digest selects response mode by request shape:
Accept: text/event-streamand nowebhook_url-> SSE modewebhook_urlpresent -> webhook mode- otherwise -> polling mode
Response Semantics by Mode
Polling mode
Returns a job response (job_id, status, created_at, job_type, stream_url, optional message).
Follow with GET /jobs/{job_id} for runtime details and summary outcomes.
Webhook mode
Returns a job response immediately, then delivers async summary/status events. Common webhooktype values:
job_startedsummary_generatedjob_stoppederror
SSE mode
Returns live text events. Common event names:startedprogresssummarystoppederror
stopped and error as terminal events for that stream session.
Tuning Semantics
window_minutes: coverage duration per summarycapture_interval_seconds: sampling cadencemax_windows: optional cap on total windows
Related
- Tuning patterns: Tune Monitoring for Latency, Accuracy, and Cost
- Job state details: Get Job Details
- Workflow chooser: Choose Your Workflow
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Headers
Body
application/json
Request to start a live digest job (SSE streaming).
YouTube Live URL or RTSP stream to digest
Required string length:
1 - 500Time window in minutes
Required range:
1 <= x <= 60Webhook URL for notifications
Required string length:
1 - 2083Frame capture interval
Required range:
10 <= x <= 300Stop after N summaries. None = run until max duration
Required range:
x >= 1Include base64 frame grid in summary events
Response
Successful Response