curl --request POST \
  --url https://be.datagol.ai/noCo/api/v2/workspaces/{workspaceId}/extraction \
  --header 'Content-Type: application/json' \
  --data @- <<EOF
{
  "title": "config test",
  "extractionMode": "ADVANCED",
  "elementType": "COLUMN",
  "elementId": "40743480-286a-4531-b3f3-7d0b68018c9d",
  "storeExtractedData": true,
  "scheduleType": "MANUAL",
  "schedule": {
    "cronExpression": ""
  },
  "outputConfiguration": {
    "createNewWorkbook": true,
    "title": "sample transcripts output"
  },
  "inputTableId": "7963e2b4-dddc-4dd4-8c44-8c70c47da692",
  "primaryKeyColumnId": [
    "ee42ef18-0d8a-461e-bae1-4370a8c13fec"
  ],
  "columnConfiguration": [
    {
      "name": "title",
      "description": "Optional title or identifier for the transcript (e.g., meeting name, interview subject).",
      "uiMetadata": {
        "title": "Title"
      },
      "uiDataType": "SINGLE_LINE_TEXT"
    },
    {
      "name": "duration_seconds",
      "description": "Total duration of the transcribed audio/video in seconds.",
      "uiMetadata": {
        "title": "Duration Seconds"
      },
      "uiDataType": "NUMBER"
    },
    {
      "name": "language_code",
      "description": "BCP-47 language code of the transcript (e.g., 'en-US', 'es-ES').",
      "uiMetadata": {
        "title": "Language Code"
      },
      "uiDataType": "SINGLE_LINE_TEXT"
    },
    {
      "name": "speaker_count",
      "description": "The total number of unique speakers identified in the transcript.",
      "uiMetadata": {
        "title": "Speaker Count"
      },
      "uiDataType": "NUMBER"
    },
    {
      "name": "segments",
      "description": "An array of spoken segments or utterances, each representing a continuous speech turn by a single speaker.",
      "uiMetadata": {
        "title": "Segments"
      },
      "uiDataType": "JSON"
    }
  ],
  "advancedSchema": {
    "type": "object",
    "additionalProperties": false,
    "properties": {
      "title": {
        "type": "string",
        "description": "Optional title or identifier for the transcript (e.g., meeting name, interview subject)."
      },
      "duration_seconds": {
        "type": "number",
        "description": "Total duration of the transcribed audio/video in seconds."
      },
      "language_code": {
        "type": "string",
        "description": "BCP-47 language code of the transcript (e.g., 'en-US', 'es-ES')."
      },
      "speaker_count": {
        "type": "number",
        "description": "The total number of unique speakers identified in the transcript."
      },
      "segments": {
        "type": "array",
        "description": "An array of spoken segments or utterances, each representing a continuous speech turn by a single speaker.",
        "items": {
          "type": "object",
          "properties": {
            "speaker": {
              "type": "string",
              "description": "Identifier for the speaker of this segment (e.g., 'Speaker 1', 'John Doe')."
            },
            "start_time": {
              "type": "number",
              "description": "The start time of the segment in seconds from the beginning of the audio/video."
            },
            "end_time": {
              "type": "number",
              "description": "The end time of the segment in seconds from the beginning of the audio/video."
            },
            "text": {
              "type": "string",
              "description": "The full transcribed text of this segment."
            },
            "confidence": {
              "type": "number",
              "description": "Confidence score for the accuracy of this segment's transcription (0.0 to 1.0)."
            },
            "words": {
              "type": "array",
              "description": "An array of individual words within this segment, with their specific timings and confidence scores.",
              "items": {
                "type": "object",
                "properties": {
                  "word": {
                    "type": "string",
                    "description": "The transcribed word."
                  },
                  "start_time": {
                    "type": "number",
                    "description": "The start time of the word in seconds relative to the beginning of the audio/video."
                  },
                  "end_time": {
                    "type": "number",
                    "description": "The end time of the word in seconds relative to the beginning of the audio/video."
                  },
                  "confidence": {
                    "type": "number",
                    "description": "Confidence score for the accuracy of this word's transcription (0.0 to 1.0)."
                  }
                },
                "required": [
                  "word",
                  "start_time",
                  "end_time"
                ]
              }
            }
          },
          "required": [
            "speaker",
            "start_time",
            "end_time",
            "text"
          ]
        }
      }
    },
    "required": [
      "segments"
    ]
  }
}
EOF