Vapi · Schema

PerformanceMetrics

AIVoiceAgentsRealtimeCPaaS

Properties

Name Type Description
turnLatencies array These are the individual latencies for each turn.
modelLatencyAverage number This is the average latency for the model to output the first token.
voiceLatencyAverage number This is the average latency for the text to speech.
transcriberLatencyAverage number This is the average latency for the transcriber.
endpointingLatencyAverage number This is the average latency for the endpointing.
turnLatencyAverage number This is the average latency for complete turns.
fromTransportLatencyAverage number This is the average latency for packets received from the transport provider in milliseconds.
toTransportLatencyAverage number This is the average latency for packets sent to the transport provider in milliseconds.
numUserInterrupted number This is the number of times the user was interrupted by the assistant during the call.
numAssistantInterrupted number This is the number of times the assistant was interrupted by the user during the call.
View JSON Schema on GitHub

JSON Schema

vapi-performancemetrics-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/PerformanceMetrics",
  "title": "PerformanceMetrics",
  "type": "object",
  "properties": {
    "turnLatencies": {
      "description": "These are the individual latencies for each turn.",
      "type": "array",
      "items": {
        "$ref": "#/components/schemas/TurnLatency"
      }
    },
    "modelLatencyAverage": {
      "type": "number",
      "description": "This is the average latency for the model to output the first token."
    },
    "voiceLatencyAverage": {
      "type": "number",
      "description": "This is the average latency for the text to speech."
    },
    "transcriberLatencyAverage": {
      "type": "number",
      "description": "This is the average latency for the transcriber."
    },
    "endpointingLatencyAverage": {
      "type": "number",
      "description": "This is the average latency for the endpointing."
    },
    "turnLatencyAverage": {
      "type": "number",
      "description": "This is the average latency for complete turns."
    },
    "fromTransportLatencyAverage": {
      "type": "number",
      "description": "This is the average latency for packets received from the transport provider in milliseconds."
    },
    "toTransportLatencyAverage": {
      "type": "number",
      "description": "This is the average latency for packets sent to the transport provider in milliseconds."
    },
    "numUserInterrupted": {
      "type": "number",
      "description": "This is the number of times the user was interrupted by the assistant during the call."
    },
    "numAssistantInterrupted": {
      "type": "number",
      "description": "This is the number of times the assistant was interrupted by the user during the call."
    }
  }
}