PollResponse

Shape varies by status. See the endpoint examples.

idstringrequired

externalIdstringnullable

statusstringrequired

Possible values: [queued, processing, success, partial, failed]

timestampdate-time

processingTimeMsinteger

scoringMethodstring

Possible values: [ml_hybrid, gpt_multilingual]

audio objectnullable

durationMsinteger

durationFormattedstring

languageCodestring

requestedLanguagestring

speakerCountinteger

candidateDetection objectnullable

speakerstring

speakerLabelstring

confidencestring

Possible values: [high, medium, low]

reasonstring

wordCountinteger

scores object

Flat score object. Scores are on a 0–5 scale; percentages are 0–100.

vocabularynumbernullable

vocabularyCefrstringnullable

vocabularyPercentintegernullable

fluencynumbernullable

fluencyCefrstringnullable

fluencyPercentintegernullable

accentnumbernullable

accentCefrstringnullable

accentPercentintegernullable

overallnumbernullable

cefrLevelstringnullable

overallPercentintegernullable

explainability objectnullable

Plain-language, ~2-3 sentence summary of why each score came out the way it did. Safe to show directly to end users (hiring managers, candidates, auditors). Only present when the heuristic scoring pipeline produced a per-dimension feature breakdown — omitted for failed runs and in rare cases where breakdowns aren't available.

vocabstring

fluencystring

analysisobjectnullable

Detailed per-dimension analysis (vocabulary, fluency, accent).

hrRecommendationstringnullable

candidateFeedbackstringnullable

transcript objectnullable

segmentsobject[]

speakersobject[]

candidateTextstring

candidateSpeakerstring

credits objectnullable

deductedinteger

remainingBalanceinteger

audioDurationMinutesnumber

error objectnullable

Present when status=failed.

codestring

messagestring

metadata object

The structured {key:value} run metadata you supplied on submit (string values). {} when none. Returned on every poll status.

property name*string

tagsstring[]

The run tags you supplied on submit (de-duped, trimmed). [] when none. Returned on every poll status.

Example: ["batch-3","eu-region"]

PollResponse

{
  "id": "string",
  "externalId": "string",
  "status": "queued",
  "timestamp": "2024-07-29T15:51:28.071Z",
  "processingTimeMs": 0,
  "scoringMethod": "ml_hybrid",
  "audio": {
    "durationMs": 0,
    "durationFormatted": "string",
    "languageCode": "string",
    "requestedLanguage": "string",
    "speakerCount": 0
  },
  "candidateDetection": {
    "speaker": "string",
    "speakerLabel": "string",
    "confidence": "high",
    "reason": "string",
    "wordCount": 0
  },
  "scores": {
    "vocabulary": 0,
    "vocabularyCefr": "string",
    "vocabularyPercent": 0,
    "fluency": 0,
    "fluencyCefr": "string",
    "fluencyPercent": 0,
    "accent": 0,
    "accentCefr": "string",
    "accentPercent": 0,
    "overall": 0,
    "cefrLevel": "string",
    "overallPercent": 0
  },
  "explainability": {
    "vocab": "string",
    "fluency": "string"
  },
  "analysis": {},
  "hrRecommendation": "string",
  "candidateFeedback": "string",
  "transcript": {
    "segments": [
      {}
    ],
    "speakers": [
      {}
    ],
    "candidateText": "string",
    "candidateSpeaker": "string"
  },
  "credits": {
    "deducted": 0,
    "remainingBalance": 0,
    "audioDurationMinutes": 0
  },
  "error": {
    "code": "string",
    "message": "string"
  },
  "metadata": {
    "candidate_id": "c_887",
    "role": "backend"
  },
  "tags": [
    "batch-3",
    "eu-region"
  ]
}