Zum Inhalt
HALOWERK

Medienwerk

diarize

Takes an audio or video file by URL or inline base64 and reports who spoke when. Every turn comes back with its speaker label, start and end time, duration, word count and text, and consecutive words from the same speaker are merged into one turn rather than left as a word list.

POST https://medien.halowerk.com/v1/diarize

Eingaben

Felder des veröffentlichten Eingabeschemas
FeldTypPflichtBeschreibung
sourceobjectJaThe recording. Either url or content_base64.
duration_minutesintegerJaLength of the recording in started minutes — this is what you are billed for. A longer file is refused with its real length and nothing is charged.
languagestringNeinBCP-47 code such as de, en. "multi" enables multilingual recognition at the provider's higher rate. Omit to detect.
include_turn_textbooleanNeinInclude the text of each turn. Off returns only the timeline and the figures.
confidence_thresholdnumberNeinWords below this confidence are listed separately.
Vollständiges Eingabeschema anzeigen
{
  "type": "object",
  "required": [
    "source",
    "duration_minutes"
  ],
  "additionalProperties": false,
  "properties": {
    "source": {
      "type": "object",
      "additionalProperties": false,
      "description": "The recording. Either url or content_base64.",
      "properties": {
        "url": {
          "type": "string",
          "maxLength": 2048,
          "description": "Public http(s) URL of the audio or video file."
        },
        "content_base64": {
          "type": "string",
          "maxLength": 12000000,
          "description": "The file inline, base64."
        },
        "filename": {
          "type": "string",
          "maxLength": 260
        }
      }
    },
    "duration_minutes": {
      "type": "integer",
      "minimum": 1,
      "maximum": 30,
      "description": "Length of the recording in started minutes — this is what you are billed for. A longer file is refused with its real length and nothing is charged."
    },
    "language": {
      "type": "string",
      "maxLength": 12,
      "description": "BCP-47 code such as de, en. \"multi\" enables multilingual recognition at the provider's higher rate. Omit to detect."
    },
    "include_turn_text": {
      "type": "boolean",
      "default": true,
      "description": "Include the text of each turn. Off returns only the timeline and the figures."
    },
    "confidence_threshold": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "default": 0.7,
      "description": "Words below this confidence are listed separately."
    }
  }
}

Originalschema öffnen

Veröffentlichtes Eingabebeispiel

{
  "source": {
    "url": "https://samplelib.com/lib/preview/mp3/sample-3s.mp3"
  },
  "duration_minutes": 1,
  "language": "en"
}

Ergebnis & Dokumentation

Maschinenlesbare Dokumentation dieses Hubs

Quelle dieser Seite: der veröffentlichte HALOWERK-Katalog. Stand: 2026-11-01, 15:19 UTC.

Weitere Endpunkte dieses Hubs

Alle Endpunkte dieses Hubs →