AudioTranscriptionResponse

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/telnyx/main/json-schema/telnyx-audio-transcription-response-schema.json",
  "title": "AudioTranscriptionResponse",
  "description": "Response fields vary by model. `distil-whisper/distil-large-v2` returns `text`, `duration`, and `segments` in `verbose_json` mode. `openai/whisper-large-v3-turbo` returns `text` only. `deepgram/nova-3` returns `text` and, depending on `model_config`, may include `words` with per-word timestamps and speaker labels.",
  "x-generated": "2026-10-08",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/telnyx-audio-api-openapi.yml#/components/schemas/AudioTranscriptionResponse",
  "properties": {
    "duration": {
      "description": "The duration of the audio file in seconds. Returned by `distil-whisper/distil-large-v2` and `deepgram/nova-3` when `response_format` is `verbose_json`. Not returned by `openai/whisper-large-v3-turbo`.",
      "type": "number"
    },
    "segments": {
      "description": "Segments of the transcribed text and their corresponding details. Returned by `distil-whisper/distil-large-v2` when `response_format` is `verbose_json`. Not returned by `openai/whisper-large-v3-turbo`.",
      "items": {
        "$ref": "#/$defs/AudioTranscriptionResponseSegments"
      },
      "type": "array"
    },
    "text": {
      "description": "The transcribed text for the audio file.",
      "type": "string"
    },
    "words": {
      "description": "Word-level timestamps and optional speaker labels. Only returned by `deepgram/nova-3` when word-level output is enabled via `model_config`.",
      "items": {
        "$ref": "#/$defs/AudioTranscriptionResponseWord"
      },
      "type": "array"
    }
  },
  "required": [
    "text"
  ],
  "type": "object",
  "$defs": {
    "AudioTranscriptionResponseSegments": {
      "properties": {
        "end": {
          "description": "End time of the segment in seconds.",
          "type": "number"
        },
        "id": {
          "description": "Unique identifier of the segment.",
          "type": "number"
        },
        "start": {
          "description": "Start time of the segment in seconds.",
          "type": "number"
        },
        "text": {
          "description": "Text content of the segment.",
          "type": "string"
        }
      },
      "required": [
        "id",
        "start",
        "end",
        "text"
      ],
      "type": "object"
    },
    "AudioTranscriptionResponseWord": {
      "description": "Word-level timing detail. Only present when using `deepgram/nova-3` with `model_config` options that enable word timestamps.",
      "properties": {
        "confidence": {
          "description": "Confidence score for the word (0.0 to 1.0).",
          "type": "number"
        },
        "end": {
          "description": "End time of the word in seconds.",
          "type": "number"
        },
        "speaker": {
          "description": "Speaker index. Only present when diarization is enabled via `model_config`.",
          "type": "integer"
        },
        "start": {
          "description": "Start time of the word in seconds.",
          "type": "number"
        },
        "word": {
          "description": "The transcribed word.",
          "type": "string"
        }
      },
      "required": [
        "word",
        "start",
        "end"
      ],
      "type": "object"
    }
  }
}