TranscriptionTask

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/oracle/main/json-schema/oracle-transcription-task-schema.json",
  "title": "TranscriptionTask",
  "description": "Description of Transcription Task.",
  "x-generated": "2026-10-03",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/oracle-aiservicespeech-api-openapi.yml#/components/schemas/TranscriptionTask",
  "properties": {
    "audioFormatDetails": {
      "$ref": "#/$defs/AudioFormatDetails"
    },
    "displayName": {
      "description": "A user-friendly display name for the task.",
      "type": "string"
    },
    "fileDurationInSeconds": {
      "description": "Duration of input file in Seconds.",
      "type": "integer"
    },
    "fileSizeInBytes": {
      "description": "Size of input file in Bytes.",
      "type": "integer"
    },
    "id": {
      "description": "The [OCID](/iaas/Content/General/Concepts/identifiers.htm) of the task.",
      "type": "string"
    },
    "inputLocation": {
      "$ref": "#/$defs/ObjectLocation"
    },
    "lifecycleDetails": {
      "description": "A message describing the current state in more detail. For example, can be used to provide actionable information for a resource in Failed state.",
      "type": "string"
    },
    "lifecycleState": {
      "description": "The current state of the Task.",
      "enum": [
        "ACCEPTED",
        "IN_PROGRESS",
        "SUCCEEDED",
        "FAILED",
        "CANCELED"
      ],
      "type": "string"
    },
    "modelDetails": {
      "$ref": "#/$defs/TranscriptionModelDetails"
    },
    "outputLocation": {
      "$ref": "#/$defs/ObjectLocation"
    },
    "percentComplete": {
      "description": "How much progress the operation has made, vs the total amount of work that must be performed.",
      "maximum": 100,
      "minimum": 0,
      "type": "integer"
    },
    "processingDurationInSeconds": {
      "description": "Task proccessing duration, which excludes waiting time in the system.",
      "type": "integer"
    },
    "timeFinished": {
      "description": "Task finished time.",
      "format": "date-time",
      "type": "string"
    },
    "timeStarted": {
      "description": "Task started time.",
      "format": "date-time",
      "type": "string"
    },
    "ttlInDays": {
      "description": "Time to live duration in days for tasks. Task will be available till max 90 days.",
      "type": "integer"
    }
  },
  "required": [
    "id"
  ],
  "type": "object",
  "$defs": {
    "AudioFormatDetails": {
      "description": "Audio format details.",
      "properties": {
        "encoding": {
          "description": "Input file encoding. Example - PCM.",
          "type": "string"
        },
        "format": {
          "description": "Input file format. Example - WAV.",
          "type": "string"
        },
        "numberOfChannels": {
          "description": "Input file number of channels.",
          "type": "integer"
        },
        "sampleRateInHz": {
          "description": "Input file sampleRate. Example - 16000",
          "type": "integer"
        }
      },
      "type": "object"
    },
    "Diarization": {
      "description": "Speaker diarization is a combination of speaker segmentation and speaker clustering. Provide diarization details to enable this feature.",
      "properties": {
        "isDiarizationEnabled": {
          "default": false,
          "description": "Set true to enable Speaker diarization and tag transcription with speaker tags. By default this is disabled.",
          "type": "boolean"
        },
        "numberOfSpeakers": {
          "description": "Number of speakers in the audio provided. By default service will auto detect all speakers in audio file",
          "maximum": 16,
          "minimum": 2,
          "type": "integer",
          "x-default-description": "null"
        }
      },
      "type": "object"
    },
    "ObjectLocation": {
      "description": "A location in Object Storage that is uniquely identified by namespace name, bucket name and object name.",
      "properties": {
        "bucketName": {
          "description": "Object Storage bucket name.",
          "maxLength": 256,
          "minLength": 1,
          "type": "string"
        },
        "namespaceName": {
          "description": "Object Storage namespace name.",
          "maxLength": 1024,
          "minLength": 1,
          "type": "string"
        },
        "objectNames": {
          "description": "Object Storage object names.",
          "items": {
            "type": "string"
          },
          "minItems": 1,
          "type": "array"
        }
      },
      "required": [
        "namespaceName",
        "bucketName",
        "objectNames"
      ],
      "type": "object"
    },
    "TranscriptionModelDetails": {
      "description": "Model details.",
      "properties": {
        "domain": {
          "default": "GENERIC",
          "description": "Domain for input files.",
          "enum": [
            "GENERIC"
          ],
          "type": "string"
        },
        "languageCode": {
          "default": "en-US",
          "description": "Oracle supported language codes are (Oracle models are locale specific).\n- en-US: English - United States (default)\n- es-ES: Spanish - Spain\n- pt-BR: Portuguese - Brazil\n- en-GB: English - Great Britain\n- en-AU: English - Australia\n- en-IN: English - India\n- hi-IN: Hindi - India\n- fr-FR: French - France\n- de-DE: German - Germany\n- it-IT: Italian - Italy\n\nWhisper supported language codes are (Whisper models are locale agnostic).\n- auto: Auto-detect language\n- af: Afrikaans\n- ar: Arabic\n- az: Azerbaijani\n- be: Belarusian\n- bg: Bulgarian\n- bs: Bosnian\n- ca: Catalan\n- cs: Czech\n- cy: Welsh\n- da: Danish\n- de: German\n- el: Greek\n- en: English (default)\n- es: Spanish\n- et: Estonian\n- fa: Persian\n- fi: Finnish\n- fr: French\n- gl: Galician\n- he: Hebrew\n- hi: Hindi\n- hr: Croatian\n- hu: Hungarian\n- hy: Armenian\n- id: Indonesian\n- is: Icelandic\n- it: Italian\n- ja: Japanese\n- kk: Kazakh\n- kn: Kannada\n- ko: Korean\n- lt: Lithuanian\n- lv: Latvian\n- mi: Maori\n- mk: Macedonian\n- mr: Marathi\n- ms: Malay\n- ne: Nepali\n- nl: Dutch\n- no: Norwegian\n- pl: Polish\n- pt: Portuguese\n- ro: Romanian\n- ru: Russian\n- sk: Slovak\n- sl: Slovenian\n- sr: Serbian\n- sv: Swedish\n- sw: Swahili\n- ta: Tamil\n- th: Thai\n- tl: Tagalog\n- tr: Turkish\n- uk: Ukrainian\n- ur: Urdu\n- vi: Vietnamese\n- zh: Chinese\n",
          "enum": [
            "en-US",
            "es-ES",
            "pt-BR",
            "en-GB",
            "en-AU",
            "en-IN",
            "hi-IN",
            "fr-FR",
            "de-DE",
            "it-IT",
            "auto",
            "af",
            "ar",
            "az",
            "be",
            "bg",
            "bs",
            "ca",
            "cs",
            "cy",
            "da",
            "de",
            "el",
            "en",
            "es",
            "et",
            "fa",
            "fi",
            "fr",
            "gl",
            "he",
            "hi",
            "hr",
            "hu",
            "hy",
            "id",
            "is",
            "it",
            "ja",
            "kk",
            "kn",
            "ko",
            "lt",
            "lv",
            "mi",
            "mk",
            "mr",
            "ms",
            "ne",
            "nl",
            "no",
            "pl",
            "pt",
            "ro",
            "ru",
            "sk",
            "sl",
            "sr",
            "sv",
            "sw",
            "ta",
            "th",
            "tl",
            "tr",
            "uk",
            "ur",
            "vi",
            "zh"
          ],
          "type": "string"
        },
        "modelType": {
          "default": "ORACLE",
          "description": "Select a model to use for generating transcriptions. Currently supported models are:\n- ORACLE\n- WHISPER_MEDIUM\n- WHISPER_LARGE_V2 (upon service request)\n- WHISPER_LARGE_V3T\n",
          "type": "string"
        },
        "transcriptionSettings": {
          "$ref": "#/$defs/TranscriptionSettings"
        }
      }
    },
    "TranscriptionSettings": {
      "default": {
        "diarization": {
          "isDiarizationEnabled": false
        }
      },
      "description": "Processes to perform on the generated transcription.",
      "properties": {
        "additionalSettings": {
          "additionalProperties": {
            "type": "string"
          },
          "description": "Simple key-value pair for setting model specific properties. For more details, refer the documentation.",
          "type": "object"
        },
        "diarization": {
          "$ref": "#/$defs/Diarization"
        }
      },
      "type": "object"
    }
  }
}