SpeechRecognitionResultAdvanced

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/cloudmersive/json-schema/cloudmersive-speech-recognition-result-advanced-schema.json",
  "title": "SpeechRecognitionResultAdvanced",
  "description": "Result of recognizing speech with the higher-accuracy file/advanced endpoint.\nWord-oriented (one entry per word, not per BPE sub-token) and produced\nfrom DTW-aligned timestamps.",
  "x-generated": "2026-11-05",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/cloudmersive-recognize-api-openapi.yml#/components/schemas/SpeechRecognitionResultAdvanced",
  "type": "object",
  "properties": {
    "TextResult": {
      "description": "Recognition result in text format",
      "type": "string"
    },
    "Words": {
      "description": "Word-level timestamps with character offsets into TextResult.\nTimestamps are derived via Dynamic Time Warping (DTW) alignment for\nsubstantially better accuracy than the default token-timestamp path.",
      "type": "array",
      "items": {
        "$ref": "#/$defs/WordTimestamp"
      }
    }
  },
  "additionalProperties": false,
  "$defs": {
    "WordTimestamp": {
      "description": "A single word with its DTW-aligned time range and position in the output text.",
      "type": "object",
      "properties": {
        "Word": {
          "description": "The word text",
          "type": "string"
        },
        "CharacterOffsetStart": {
          "format": "int32",
          "description": "Start character offset (0-based) in TextResult",
          "type": "integer"
        },
        "CharacterOffsetEnd": {
          "format": "int32",
          "description": "End character offset (exclusive) in TextResult",
          "type": "integer"
        },
        "StartTimeMs": {
          "format": "int64",
          "description": "Start time of this word in the audio, in milliseconds",
          "type": "integer"
        },
        "EndTimeMs": {
          "format": "int64",
          "description": "End time of this word in the audio, in milliseconds",
          "type": "integer"
        }
      },
      "additionalProperties": false
    }
  }
}