GET

/v1/schemas/openai/audio/audio%2Fvoices

kind inputactivity audiohash db4fe2ec…extracted Oct 17, 2026version currentsource upstream spec ↗

Request 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/voices",
  "kind": "input",
  "contentHash": "db4fe2ec5e2e912dcb751e39eb8fc4e54f7816c85c1e60e40c3ce4d7a6c2a985",
  "specRevision": "2b51350e06a736e11612f8c04fe0028009c87380d622bf8b8d7e9bbc4ad81bcc",
  "provenance": {
    "sourceUrl": "https://raw.githubusercontent.com/openai/openai-node/main/api_reference/openapi.transformed.yml",
    "sourceHash": "2b51350e06a736e11612f8c04fe0028009c87380d622bf8b8d7e9bbc4ad81bcc",
    "fetchedAt": 1792213805,
    "extractorVersion": "1",
    "derivation": "upstream-spec",
    "verifiedAt": null
  },
  "createdAt": 1792213805,
  "supersededAt": null,
  "schema": {
    "discriminator": {
      "propertyName": "type",
      "mapping": {
        "audio_sample": "#/components/schemas/CreateVoiceFromConsentRequest",
        "prompt": "#/components/schemas/CreateVoicePromptRequest"
      }
    },
    "x-oai-default-discriminator-value": "audio_sample",
    "anyOf": [
      {
        "$ref": "#/$defs/CreateVoiceFromConsentRequest"
      },
      {
        "$ref": "#/$defs/CreateVoicePromptRequest"
      }
    ],
    "$defs": {
      "CreateVoiceFromConsentRequest": {
        "type": "object",
        "title": "Consent",
        "description": "Creates a voice from a consent recording and an audio sample. Requires multipart/form-data.",
        "additionalProperties": false,
        "properties": {
          "type": {
            "type": "string",
            "enum": [
              "audio_sample"
            ],
            "default": "audio_sample",
            "description": "The voice creation method. Defaults to `audio_sample` when omitted."
          },
          "name": {
            "type": "string",
            "minLength": 1,
            "maxLength": 256,
            "description": "The name of the new voice."
          },
          "audio_sample": {
            "type": "string",
            "format": "binary",
            "x-oaiTypeLabel": "file",
            "description": "The sample audio recording file. Maximum size is 10 MiB.\n\nSupported MIME types:\n`audio/mpeg`, `audio/wav`, `audio/x-wav`, `audio/ogg`, `audio/aac`, `audio/flac`, `audio/webm`, `audio/mp4`.\n"
          },
          "consent": {
            "type": "string",
            "description": "The consent recording ID (for example, `cons_1234`)."
          }
        },
        "required": [
          "name",
          "audio_sample",
          "consent"
        ]
      },
      "CreateVoicePromptRequest": {
        "type": "object",
        "title": "Prompt",
        "description": "Creates a synthetic voice from a text description. Supports application/json or multipart/form-data.",
        "additionalProperties": false,
        "properties": {
          "type": {
            "type": "string",
            "enum": [
              "prompt"
            ],
            "description": "Set to `prompt` to create a voice from a text description."
          },
          "name": {
            "type": "string",
            "minLength": 1,
            "maxLength": 256,
            "description": "The name of the new voice."
          },
          "prompt": {
            "type": "string",
            "minLength": 1,
            "maxLength": 2000,
            "description": "A description of the desired voice. Must not contain only whitespace."
          },
          "script_hint": {
            "type": "string",
            "minLength": 1,
            "maxLength": 2000,
            "description": "Optional text for the voice to speak during creation. If omitted, a script is generated from the prompt. Must not be blank after trimming whitespace; scripts that are too short are rejected."
          },
          "model": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "string",
                "enum": [
                  "auto",
                  "2026-10-08"
                ]
              }
            ],
            "default": "auto",
            "description": "The voice creation model to use. Defaults to `auto`."
          }
        },
        "required": [
          "type",
          "name",
          "prompt"
        ]
      }
    }
  }
}

Validate a payload

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