/v1/schemas/openai/audio/audio/translations?kind=output

{
  "provider": "openai",
  "activity": "audio",
  "endpointId": "audio/translations",
  "kind": "output",
  "contentHash": "64a6b743e3475ff0dbbc387fa46bff474f418aac99436dae17ce8b9a790a72b1",
  "specRevision": "49bac5ba25ea5ce2dfd77d18652ae21b60f5880d5b9373e30942d2be88b8be88",
  "provenance": {
    "sourceUrl": "https://raw.githubusercontent.com/openai/openai-node/main/api_reference/openapi.transformed.yml",
    "sourceHash": "49bac5ba25ea5ce2dfd77d18652ae21b60f5880d5b9373e30942d2be88b8be88",
    "fetchedAt": 1786770656,
    "extractorVersion": "1",
    "derivation": "upstream-spec",
    "verifiedAt": null
  },
  "createdAt": 1786770656,
  "supersededAt": null,
  "schema": {
    "anyOf": [
      {
        "$ref": "#/$defs/CreateTranslationResponseJson"
      },
      {
        "$ref": "#/$defs/CreateTranslationResponseVerboseJson",
        "x-stainless-skip": [
          "go"
        ]
      }
    ],
    "$defs": {
      "CreateTranslationResponseJson": {
        "type": "object",
        "properties": {
          "text": {
            "type": "string"
          }
        },
        "required": [
          "text"
        ]
      },
      "CreateTranslationResponseVerboseJson": {
        "type": "object",
        "properties": {
          "language": {
            "type": "string",
            "description": "The language of the output translation (always `english`)."
          },
          "duration": {
            "type": "number",
            "format": "double",
            "description": "The duration of the input audio."
          },
          "text": {
            "type": "string",
            "description": "The translated text."
          },
          "segments": {
            "type": "array",
            "description": "Segments of the translated text and their corresponding details.",
            "items": {
              "$ref": "#/$defs/TranscriptionSegment"
            }
          }
        },
        "required": [
          "language",
          "duration",
          "text"
        ]
      },
      "TranscriptionSegment": {
        "type": "object",
        "properties": {
          "id": {
            "type": "integer",
            "description": "Unique identifier of the segment."
          },
          "seek": {
            "type": "integer",
            "description": "Seek offset of the segment."
          },
          "start": {
            "type": "number",
            "format": "double",
            "description": "Start time of the segment in seconds."
          },
          "end": {
            "type": "number",
            "format": "double",
            "description": "End time of the segment in seconds."
          },
          "text": {
            "type": "string",
            "description": "Text content of the segment."
          },
          "tokens": {
            "type": "array",
            "items": {
              "type": "integer"
            },
            "description": "Array of token IDs for the text content."
          },
          "temperature": {
            "type": "number",
            "format": "float",
            "description": "Temperature parameter used for generating the segment."
          },
          "avg_logprob": {
            "type": "number",
            "format": "float",
            "description": "Average logprob of the segment. If the value is lower than -1, consider the logprobs failed."
          },
          "compression_ratio": {
            "type": "number",
            "format": "float",
            "description": "Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed."
          },
          "no_speech_prob": {
            "type": "number",
            "format": "float",
            "description": "Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent."
          }
        },
        "required": [
          "id",
          "seek",
          "start",
          "end",
          "text",
          "tokens",
          "temperature",
          "avg_logprob",
          "compression_ratio",
          "no_speech_prob"
        ]
      }
    }
  }
}