Skip to main content

Summaries

AI summaries condense a call into a short explanation, outcome, sentiment, action items, and key points. Use them to make review queues faster.

AI results are read after a call has completed and recorded audio has been processed. The public API exposes read endpoints for combined AI, transcription, summaries, scoring, and topics. Your integration should store the returned status and payload so the UI can show completed, missing, and failed states separately.

Real Request​

curl -sS https://api.minivoice.eu/v1/calls/call_123/ai-summary \
  -H 'Authorization: Bearer $MINIVOICE_API_KEY'

Real Response​

{
  "data": {
    "status": "completed",
    "summary": "The caller asked why the latest invoice was higher than expected.",
    "outcome": "follow_up_needed",
    "sentiment": "neutral",
    "action_items": [
      "Review the invoice and call the customer back"
    ],
    "key_points": [
      "Invoice question",
      "Customer requested follow-up"
    ]
  }
}

Real Webhook Example​

{
  "event": "call.completed",
  "created_at": "2026-05-29T12:10:00Z",
  "call": {
    "id": "call_123",
    "customer_id": "cust_123",
    "application_id": "app_123",
    "status": "completed",
    "direction": "outbound",
    "from": "+15551230001",
    "to": "+15551230002"
  },
  "variables": {},
  "data": {}
}

Common Use Case​

Show summary cards in a support queue so agents can scan the issue, outcome, and action items before reading the full transcript.

Common Failure Case​

{
  "error": {
    "code": "ai_summary_not_found",
    "message": "AI summary not found"
  }
}

Do not hide the call when one AI result is missing. Show the call metadata immediately and let each AI section render its own completed or unavailable state.

Response handling

AI endpoints should be consumed as enrichment, not as the primary call record. Store the call ID, result status, and raw response for each feature your product uses. A completed call can have a completed transcript and a missing score, or a completed summary and no topics. Model those states independently in your UI and data layer.

For dashboards, prefer progressive loading. Show the call metadata first, then render transcript, summary, score, sentiment, and topics as each read succeeds. For automations, branch on explicit result values and status fields instead of assuming every recorded call has the same AI outputs.

Display guidance

A useful summary view shows the summary text first, then outcome, sentiment, action items, and key points. Keep action items visually separate from key points because action items usually drive follow-up work, while key points support review and search.

Testing​

Place a recorded call with known wording, wait for call.completed, then fetch this endpoint. Save the response as a fixture and test your parser against completed data plus the not-found response shown above.