GET

/v1/schemas/openai/audio/audio%2Fspeech?kind=output

kind outputactivity audiohash d3a4a4a2…extracted Nov 5, 2026version currentsource upstream spec ↗

Response body

0 properties · 0 required · 0 $defs

This schema isn’t a plain object with properties — showing the raw JSON instead.

application/json
{
  "provider": "openai",
  "activity": "audio",
  "endpointId": "audio/speech",
  "kind": "output",
  "contentHash": "d3a4a4a25325f285a20827d8e15774de076c2a004f5082c5d1e50efb5cbf5ce6",
  "specRevision": "898eefefea6b5dc52da42f5628a64a0ffba65d850282e1cb59ab459f7e356f92",
  "provenance": {
    "sourceUrl": "https://raw.githubusercontent.com/openai/openai-node/main/api_reference/openapi.transformed.yml",
    "sourceHash": "898eefefea6b5dc52da42f5628a64a0ffba65d850282e1cb59ab459f7e356f92",
    "fetchedAt": 1793851833,
    "extractorVersion": "1",
    "derivation": "upstream-spec",
    "verifiedAt": null
  },
  "createdAt": 1793851833,
  "supersededAt": null,
  "schema": {
    "anyOf": [
      {
        "$ref": "#/$defs/SpeechAudioDeltaEvent"
      },
      {
        "$ref": "#/$defs/SpeechAudioDoneEvent"
      }
    ],
    "discriminator": {
      "propertyName": "type"
    },
    "$defs": {
      "SpeechAudioDeltaEvent": {
        "type": "object",
        "description": "Emitted for each chunk of audio data generated during speech synthesis.",
        "properties": {
          "type": {
            "type": "string",
            "description": "The type of the event. Always `speech.audio.delta`.\n",
            "enum": [
              "speech.audio.delta"
            ],
            "x-stainless-const": true
          },
          "audio": {
            "type": "string",
            "description": "A chunk of Base64-encoded audio data.\n"
          }
        },
        "required": [
          "type",
          "audio"
        ],
        "x-oaiMeta": {
          "name": "Stream Event (speech.audio.delta)",
          "group": "speech",
          "example": "{\n  \"type\": \"speech.audio.delta\",\n  \"audio\": \"base64-encoded-audio-data\"\n}\n"
        }
      },
      "SpeechAudioDoneEvent": {
        "type": "object",
        "description": "Emitted when the speech synthesis is complete and all audio has been streamed.",
        "properties": {
          "type": {
            "type": "string",
            "description": "The type of the event. Always `speech.audio.done`.\n",
            "enum": [
              "speech.audio.done"
            ],
            "x-stainless-const": true
          },
          "usage": {
            "type": "object",
            "description": "Token usage statistics for the request.\n",
            "properties": {
              "input_tokens": {
                "type": "integer",
                "description": "Number of input tokens in the prompt."
              },
              "output_tokens": {
                "type": "integer",
                "description": "Number of output tokens generated."
              },
              "total_tokens": {
                "type": "integer",
                "description": "Total number of tokens used (input + output)."
              }
            },
            "required": [
              "input_tokens",
              "output_tokens",
              "total_tokens"
            ]
          }
        },
        "required": [
          "type",
          "usage"
        ],
        "x-oaiMeta": {
          "name": "Stream Event (speech.audio.done)",
          "group": "speech",
          "example": "{\n  \"type\": \"speech.audio.done\",\n  \"usage\": {\n    \"input_tokens\": 14,\n    \"output_tokens\": 101,\n    \"total_tokens\": 115\n  }\n}\n"
        }
      }
    }
  }
}

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"openai","endpointId":"audio/speech","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}