GET

/v1/schemas/together/audio/v1%2Faudio%2Ftranscriptions?kind=output

kind outputactivity audiohash e486dc4d…extracted Oct 22, 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": "together",
  "activity": "audio",
  "endpointId": "v1/audio/transcriptions",
  "kind": "output",
  "contentHash": "e486dc4dcaef115633cff60e7981fb58877ae008f090b28f09a7abd35231f061",
  "specRevision": null,
  "provenance": {
    "sourceUrl": "https://docs.together.ai/openapi.yaml",
    "sourceHash": "bb5257b3173a2cae6d65f4f551e7e94d480a9ba5a50ba4fb91f462cb095feb06",
    "fetchedAt": 1792645913,
    "extractorVersion": "1",
    "derivation": "upstream-spec",
    "verifiedAt": null
  },
  "createdAt": 1792645913,
  "supersededAt": null,
  "schema": {
    "oneOf": [
      {
        "$ref": "#/$defs/AudioTranscriptionJsonResponse"
      },
      {
        "$ref": "#/$defs/AudioTranscriptionVerboseJsonResponse"
      }
    ],
    "$defs": {
      "AudioTranscriptionJsonResponse": {
        "type": "object",
        "required": [
          "text"
        ],
        "properties": {
          "text": {
            "type": "string",
            "description": "The transcribed text",
            "example": "Hello, world!"
          }
        }
      },
      "AudioTranscriptionSegment": {
        "type": "object",
        "required": [
          "id",
          "start",
          "end",
          "text"
        ],
        "properties": {
          "id": {
            "type": "integer",
            "description": "Unique identifier for the segment",
            "example": 0
          },
          "start": {
            "type": "number",
            "description": "Start time of the segment in seconds",
            "example": 0
          },
          "end": {
            "type": "number",
            "description": "End time of the segment in seconds",
            "example": 3.5
          },
          "text": {
            "type": "string",
            "description": "The text content of the segment",
            "example": "Hello, world!"
          }
        }
      },
      "AudioTranscriptionSpeakerSegment": {
        "type": "object",
        "required": [
          "speaker_id",
          "start",
          "end",
          "words",
          "text",
          "id"
        ],
        "properties": {
          "speaker_id": {
            "type": "string",
            "description": "The speaker identifier",
            "example": "SPEAKER_00"
          },
          "start": {
            "type": "number",
            "description": "Start time of the speaker segment in seconds",
            "example": 0
          },
          "end": {
            "type": "number",
            "description": "End time of the speaker segment in seconds",
            "example": 30.02
          },
          "words": {
            "type": "array",
            "items": {
              "$ref": "#/$defs/AudioTranscriptionWord"
            },
            "description": "Array of words spoken by this speaker in this segment"
          },
          "text": {
            "type": "string",
            "description": "The full text spoken by this speaker in this segment",
            "example": "Hello, how are you doing today?"
          },
          "id": {
            "type": "integer",
            "description": "Unique identifier for the speaker segment",
            "example": 1
          }
        }
      },
      "AudioTranscriptionVerboseJsonResponse": {
        "type": "object",
        "required": [
          "language",
          "duration",
          "text",
          "segments"
        ],
        "properties": {
          "language": {
            "type": "string",
            "description": "The language of the audio",
            "example": "english"
          },
          "duration": {
            "type": "number",
            "description": "The duration of the audio in seconds",
            "example": 3.5
          },
          "text": {
            "type": "string",
            "description": "The transcribed text",
            "example": "Hello, world!"
          },
          "segments": {
            "type": "array",
            "items": {
              "$ref": "#/$defs/AudioTranscriptionSegment"
            },
            "description": "Array of transcription segments"
          },
          "words": {
            "type": "array",
            "items": {
              "$ref": "#/$defs/AudioTranscriptionWord"
            },
            "description": "Array of transcription words (only when timestamp_granularities includes 'word')"
          },
          "speaker_segments": {
            "type": "array",
            "items": {
              "$ref": "#/$defs/AudioTranscriptionSpeakerSegment"
            },
            "description": "Array of transcription speaker segments (only when diarize is enabled)"
          }
        }
      },
      "AudioTranscriptionWord": {
        "type": "object",
        "required": [
          "word",
          "start",
          "end"
        ],
        "properties": {
          "word": {
            "type": "string",
            "description": "The word",
            "example": "Hello"
          },
          "start": {
            "type": "number",
            "description": "Start time of the word in seconds",
            "example": 0
          },
          "end": {
            "type": "number",
            "description": "End time of the word in seconds",
            "example": 0.5
          },
          "speaker_id": {
            "type": "string",
            "description": "The speaker id for the word (only when diarize is enabled)",
            "example": "SPEAKER_00"
          }
        }
      }
    }
  }
}

Validate a payload

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