This is a beta feature. To generate Latency reports, enable capturing latency metrics by configuring these call control parameters:
notifySttLatency = truevadEnable = truevadVendor = sileroGenerating the Report
- On the Reports tab, select New Report.
- In the list of reports, choose Latency Report.
- Enter the Report Name and Report Description.
- Select a Duration.
-
Select Data Filters from the following P90 values:
P90 Values Threshold Values (ms) P90 End-to-End Latency For example, 200 ms P90 ASR Latency For example, 200 ms P90 Bot Response Time For example, 200 ms P90 TTS Latency For example, 200 ms Each P90 value can be evaluated using the following conditions: Greater than or equal to (≥), Less than or equal to (≤), Greater than (>), Less than (<), Equal to (=). -
Select Report Generation and choose from the following options:
- Run On Demand
-
Schedule — You can create up to six schedules (only one if you select Hourly).

- Select Format: CSV
- Enter a Send To address (single email address or mailing list).
-
Select Create.

-
An instance of the Latency Report is generated.

-
Select the Run icon next to the report instance.

-
Select the CSV icon to generate the report output.

The red dot beside the report indicates it was generated within the last 24 hours. You can download, save, and view the report in CSV format.
-
The system generates the Latency Report.

Report Fields
| Field | Description | Example |
|---|---|---|
| Session ID | Unique identifier for each interaction session. | a12b34c56d |
| Start Time | Timestamp when the session started. | 2025-09-24 10:56:34 |
| Agent | Name of the agent handling the session. | John Doe |
| Agent Email | Email address of the agent. | john.doe@example.com |
| Queue Name | Name of the queue the interaction routes through. | Support_Queue |
| Customer | Identifier or name of the customer involved in the session. | Jane Doe |
| Duration | Total time the session lasted. | 00:12:45 |
| P90 ASR Latency (ms) | 90th percentile latency of Automatic Speech Recognition, in milliseconds. Indicates how long speech-to-text processing takes. | 250 |
| P90 Bot Latency (ms) | 90th percentile latency for the bot’s response processing, in milliseconds. Shows system responsiveness. | 120 |
| P90 TTS Latency (ms) | 90th percentile latency of Text-to-Speech processing, in milliseconds. Represents the time to convert text into audio. | 180 |
| P90 End To End Latency (ms) | 90th percentile overall latency from customer speech to agent/bot reply, in milliseconds. Combines ASR, bot, and TTS processing times. | 600 |