Voice-to-voice and LLM-TTFT percentiles over the turn ledger
GET
/v1/analytics/latency
const url = 'https://api.vocapable.com/v1/analytics/latency';const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}curl --request GET \ --url https://api.vocapable.com/v1/analytics/latency \ --header 'Authorization: Bearer <token>'Authorizations
Section titled “Authorizations”Parameters
Section titled “Parameters”Query Parameters
Section titled “Query Parameters”start
group_by
Responses
Section titled “Responses”Successful Response
Media typeapplication/json
LatencyReport
object
window
required
ReportWindow
The half-open window the report was actually computed over.
object
start
required
Start
string format: date-time
end
required
End
string format: date-time
group_by
Group By
Array<string>
buckets
Buckets
Array<object>
LatencyBucketOutTurn-latency percentiles for one group; null means the group had no sample.
object
turns
required
Turns
integer
voice_to_voice_samples
required
Voice To Voice Samples
integer
llm_ttft_samples
required
Llm Ttft Samples
integer
Example
{ "group_by": [ "campaign" ]}Validation Error
Media typeapplication/json
HTTPValidationError
object
detail
Detail
Array<object>
ValidationErrorobject
loc
required
Location
Array
msg
required
Message
string
type
required
Error Type
string
input
Input
ctx
Context
object
Examplegenerated
{ "detail": [ { "loc": [ "example" ], "msg": "example", "type": "example", "input": "example", "ctx": {} } ]}