curl --request GET \
--url https://app.thinnest.ai/api/v1/calls/{id}/timeline \
--header 'Authorization: Bearer <token>'const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://app.thinnest.ai/api/v1/calls/{id}/timeline', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));import requests
url = "https://app.thinnest.ai/api/v1/calls/{id}/timeline"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text){
"id": "out_9f2c1a44-6b0e-4c1d-8a7f-2e5b3c9d1f60",
"callRef": "out_9f2c1a44-6b0e-4c1d-8a7f-2e5b3c9d1f60",
"status": "completed",
"agent": {
"id": "ag_5c4a5f93-2b1e-4d7a-9f60-8e2d1c3b4a71",
"name": "Skyline Sales"
},
"startedAt": "2026-10-06T04:30:02.118Z",
"endedAt": "2026-10-06T04:33:11.902Z",
"timeline": {
"v": 1,
"turns": [
{
"turn": 1,
"callerStoppedAtMs": 12400,
"earPausedMs": 520,
"transcriptMs": 710,
"judgeDecidedMs": 905,
"turnDecidedMs": 910,
"modelAskedMs": 40,
"answerTextMs": 1850,
"firstAudioMs": 1330,
"firstAudioKind": "filler",
"answerAudioMs": 2310,
"answerAudioEstimated": true,
"split": {
"waitBeforeDecisionMs": 910,
"recogniserMs": 710,
"earCheckMs": 195,
"modelFirstSentenceMs": 1810,
"voiceMs": 460
}
}
]
}
}Get Call Timeline
Where the time went in each turn of one call. Every time is in milliseconds from the moment the caller stopped speaking, so a turn reads as a row of steps: the recogniser’s wait and the caller’s final words, Ear’s check, the turn being decided, the model being asked, the first words of the answer leaving the model, the first sound of any kind, and the answer being heard. split adds up the pieces a team works on: the wait before the turn was decided, the recogniser, Ear’s check, the model’s first sentence and the voice.
answerAudioMs is the time to the first word of the ACTUAL answer. quality.responseMs stops at the first sound of any kind, so a thinking line that plays first ends it; here firstAudioKind says what spoke first (answer, filler or other) and answerAudioEstimated is true when a filler spoke first and the answer’s start is worked out from the audio queued behind it rather than heard directly. A step that did not happen on a turn is null, never zero. A negative modelAskedMs is real: with earlyAnswers the model is asked before the turn is decided.
timeline is null for a call that has none: a call from before this existed, or one on a call type that does not record it. It holds times only, no words, so it stays when a call’s content is deleted. Any id List Calls hands out works.
curl --request GET \
--url https://app.thinnest.ai/api/v1/calls/{id}/timeline \
--header 'Authorization: Bearer <token>'const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
fetch('https://app.thinnest.ai/api/v1/calls/{id}/timeline', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));import requests
url = "https://app.thinnest.ai/api/v1/calls/{id}/timeline"
headers = {"Authorization": "Bearer <token>"}
response = requests.get(url, headers=headers)
print(response.text){
"id": "out_9f2c1a44-6b0e-4c1d-8a7f-2e5b3c9d1f60",
"callRef": "out_9f2c1a44-6b0e-4c1d-8a7f-2e5b3c9d1f60",
"status": "completed",
"agent": {
"id": "ag_5c4a5f93-2b1e-4d7a-9f60-8e2d1c3b4a71",
"name": "Skyline Sales"
},
"startedAt": "2026-10-06T04:30:02.118Z",
"endedAt": "2026-10-06T04:33:11.902Z",
"timeline": {
"v": 1,
"turns": [
{
"turn": 1,
"callerStoppedAtMs": 12400,
"earPausedMs": 520,
"transcriptMs": 710,
"judgeDecidedMs": 905,
"turnDecidedMs": 910,
"modelAskedMs": 40,
"answerTextMs": 1850,
"firstAudioMs": 1330,
"firstAudioKind": "filler",
"answerAudioMs": 2310,
"answerAudioEstimated": true,
"split": {
"waitBeforeDecisionMs": 910,
"recogniserMs": 710,
"earCheckMs": 195,
"modelFirstSentenceMs": 1810,
"voiceMs": 460
}
}
]
}
}Authorizations
Your API key (ta_live_…) from Settings → API keys, sent as Authorization: Bearer <key>. Keep it on a server: it can message every customer you have. A key is full, build or read-only; a request its level does not allow is refused with 403.
Headers
Developers only: the customer workspace this request acts in — its org_… id from POST /customers. Leave it out to act in your own workspace. Refused with 404 (Workspace not found.) when the id is unknown, is not one of your customers, or is not an org_… id; 410 when that customer was deleted (restore it with POST /customers/{id}/restore until it is erased); 403 when the key belongs to one customer workspace (it cannot act as another); 400 when your workspace is not a developer workspace. /customers/* and GET /customers/usage are your own workspace's and refuse the header with 400: call them without it.
"org_3fKq9TzQ1mN8vB2xR7cLpA"
Path Parameters
The call's id as Place Call or List Calls gave it: out_… or sch_… for a call you placed, the call reference for any other.
"out_9f2c1a44-6b0e-4c1d-8a7f-2e5b3c9d1f60"
Response
The call's timeline.
The call's id, as List Calls hands it out.
The call reference.
The call's status.
The agent that took the call.
Show child attributes
Show child attributes
Null for a call that has none: from before this existed, or on a call type that does not record it.
Show child attributes
Show child attributes