Skip to content
OnCoreDocs
Transcriber Tests

POSThttps://core-api.heysadie.ai/full-call-runs/{id}/rescore

id relabel success data run organizationId bankId candidateTranscriberId selection callIds calibrationTurns callCount estimate calls callerTurns audioSeconds estimatedCostUsd status analysisSampled error createdBy createdAt startedAt finishedAt metadata timestamp version path code message details field runId

Rescore a full-call run

Refresh every turn's expected text from the flag now on its line, and recompute every attempt from its stored text, at no STT cost. Use it after flags on the run's calls were added or edited. `relabel: true` also queues a fresh LLM analysis (labels, patterns, verdict), which costs tokens and moves the run back to analyzing; poll GET /full-call-runs/:id again. Errors: 404 RESOURCE_NOT_FOUND when the run is not in the organization. With `relabel`: 409 RUN_ACTIVE (`details.runId` is this run) while the run is queued, running or analyzing, and 409 RUN_CANCELLED for a cancelled run, which can never be relabeled. Offer relabel only on a completed or error run.

Try it in the API Explorer

Example request

Terminal
curl -X POST "https://core-api.heysadie.ai/full-call-runs/FULL_CALL_RUN_ID/rescore" \
  -H "Authorization: ApiKey YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "relabel": true
  }'

Authentication

Authenticate with an API key in the Authorization header using the ApiKey scheme. See Authentication for how keys work and where to get them.

Authorizationstringrequired

API key in the ApiKey scheme: ApiKey YOUR_API_KEY. Tenant keys authorize their own tenant; organization keys can act on any tenant in the organization.

X-Tenant-Idstring (uuid)optional

Required when authenticating with an organization key: it selects the tenant the request acts on. Omit with tenant keys.

Request

Path parameters

idstringrequired

A full-call run of the organization

Body application/json · required

relabelbooleanoptional

Also re-run the judge's labels, patterns and verdict, which costs LLM tokens. Only for a completed or error run, else 409 RUN_ACTIVE. Default false

Responses

200The run, rescored
successbooleanrequired

true on every 2xx

dataobjectoptional

The result

Show 1 child properties
runobjectrequired

A full-call run: one candidate replayed on every caller line of up to 10 calls and compared with production

Show 15 child properties
idstringrequired

Run id

organizationIdstringrequired

The organization that owns the run

bankIdstringrequired

The bank the run belongs to

candidateTranscriberIdstringrequired

The candidate replayed

selectionobjectrequired

The calls asked for

Show 1 child properties
callIdsstring[]required

The calls the run replays, in the order they were asked for

calibrationTurnsstring (integer) | integerrequired

Random turns asked for on which production is also replayed

callCountstring (integer) | integerrequired

Calls the run snapshotted

estimateobjectrequired

What the run replays and costs, as estimated at creation

Show 4 child properties
callsstring (integer) | integerrequired

Selected calls with a caller turn

callerTurnsstring (integer) | integerrequired

Caller lines with audio bounds; each becomes a turn

audioSecondsnumberrequired

Audio the worker replays: every turn through the candidate, plus the calibration sample through production

estimatedCostUsdnumberrequired

STT cost in USD, 6 decimals

statusenumrequired

queued: waiting for a worker. running: the candidate is replaying the turns. analyzing: the LLM judge is labeling the differing turns and writing patterns and a verdict. completed: done. cancelled: stopped by POST /full-call-runs/:id/cancel. error: failed, see `error`. queued, running and analyzing can still change; poll until completed, cancelled or error

Allowed values:"queued""running""analyzing""completed""cancelled""error"
analysisSampledbooleanrequired

The differing turns outnumbered what the analysis takes (2000), so it labeled a sample

errorstring | nullrequired

Why the run failed. Null unless status is error

createdBystring | nullrequired

Who made it, as the creating request named them in an `X-On-Behalf-Of` header. Null when it sent none

createdAtstring (date-time) | string (date) | number | nullrequired

When it was created, UTC

startedAtstring (date-time) | string (date) | number | nullrequired

When its first job was dispatched to a worker, UTC

finishedAtstring (date-time) | string (date) | number | nullrequired

When it completed, failed or was cancelled, UTC

metadataobjectoptional

Request metadata

Show 3 child properties
timestampstringrequired

When the server answered, ISO 8601 UTC

versionstringrequired

API version

pathstringoptional

The URL that was requested

400VALIDATION_ERROR: a path id, query parameter or body field broke a rule; `details` lists each `field` and its `message`. A body with a missing field or a JSON type the schema does not allow answers 400 with code INTERNAL_SERVER_ERROR and no `details` instead, so branch on the status
successbooleanrequired

false on every error

errorobjectoptional

What went wrong: a stable `code` to branch on and a human-readable `message`

Show 3 child properties
codeenumrequired

A parameter or body field broke a rule

Allowed values:"VALIDATION_ERROR"
messagestringrequired

Human-readable explanation. Do not parse it; branch on `code`

detailsobject[]optional

One entry per field that failed

Show 2 item properties
fieldstringrequired

The offending field

messagestringrequired

The rule it broke

metadataobjectoptional

Request metadata

Show 3 child properties
timestampstringrequired

When the server answered, ISO 8601 UTC

versionstringrequired

API version

pathstringoptional

The URL that was requested

401UNAUTHORIZED: no valid credentials, or a dashboard token that names no organization. Send `Authorization: ApiKey <organization API key>`
successbooleanrequired

false on every error

errorobjectoptional

What went wrong: a stable `code` to branch on and a human-readable `message`

Show 2 child properties
codeenumrequired

No valid credentials

Allowed values:"UNAUTHORIZED"
messagestringrequired

Human-readable explanation. Do not parse it; branch on `code`

metadataobjectoptional

Request metadata

Show 3 child properties
timestampstringrequired

When the server answered, ISO 8601 UTC

versionstringrequired

API version

pathstringoptional

The URL that was requested

403ORG_SCOPE_REQUIRED: transcriber testing is an organization feature. Use an organization API key without `X-Tenant-Id`, or a dashboard token scoped to the organization. A tenant API key, an organization key sent with `X-Tenant-Id` for one of its tenants, or a token carrying a tenant gets this 403. FORBIDDEN: an organization key sent `X-Tenant-Id` for a tenant outside its organization
successbooleanrequired

false on every error

errorobjectoptional

What went wrong: a stable `code` to branch on and a human-readable `message`

Show 2 child properties
codeenumrequired

ORG_SCOPE_REQUIRED: the credentials carry a tenant scope. FORBIDDEN: an organization key sent `X-Tenant-Id` for a tenant outside its organization

Allowed values:"ORG_SCOPE_REQUIRED""FORBIDDEN"
messagestringrequired

Human-readable explanation. Do not parse it; branch on `code`

metadataobjectoptional

Request metadata

Show 3 child properties
timestampstringrequired

When the server answered, ISO 8601 UTC

versionstringrequired

API version

pathstringoptional

The URL that was requested

404RESOURCE_NOT_FOUND: an id in the path, query or body names nothing in the caller's organization. `message` names what, e.g. "Transcriber bank not found"
successbooleanrequired

false on every error

errorobjectoptional

What went wrong: a stable `code` to branch on and a human-readable `message`

Show 2 child properties
codeenumrequired

An id names nothing the caller can see

Allowed values:"RESOURCE_NOT_FOUND"
messagestringrequired

Human-readable explanation. Do not parse it; branch on `code`

metadataobjectoptional

Request metadata

Show 3 child properties
timestampstringrequired

When the server answered, ISO 8601 UTC

versionstringrequired

API version

pathstringoptional

The URL that was requested

409RUN_ACTIVE: the run is still queued, running or analyzing; relabel once it is completed or error. RUN_CANCELLED: the run was cancelled, so it has nothing to relabel; start a new run instead
successbooleanrequired

false on every error

errorobjectoptional

One of two refusals, told apart by `code`

Show 6 properties across 2 possible shapes
codeenumrequired

The run is still queued, running or analyzing

Allowed values:"RUN_ACTIVE"
messagestringrequired

Human-readable explanation. Do not parse it; branch on `code`

detailsobjectrequired

The run

Show 1 child properties
runIdstringrequired

The run

codeenumrequired

The run was cancelled and can never be relabeled

Allowed values:"RUN_CANCELLED"
messagestringrequired

Human-readable explanation. Do not parse it; branch on `code`

detailsobjectrequired

The run

Show 1 child properties
runIdstringrequired

The run

metadataobjectoptional

Request metadata

Show 3 child properties
timestampstringrequired

When the server answered, ISO 8601 UTC

versionstringrequired

API version

pathstringoptional

The URL that was requested

500An unexpected server error
successbooleanrequired

false on every error

errorobjectoptional

What went wrong: a stable `code` to branch on and a human-readable `message`

Show 2 child properties
codeenumrequired

An unexpected server failure

Allowed values:"INTERNAL_SERVER_ERROR"
messagestringrequired

Human-readable explanation. Do not parse it; branch on `code`

metadataobjectoptional

Request metadata

Show 3 child properties
timestampstringrequired

When the server answered, ISO 8601 UTC

versionstringrequired

API version

pathstringoptional

The URL that was requested