GET
/v1/schemas/together/audio/audio%2Ftranslations?kind=output
Accept:
Response body
0 properties · 0 required · 0 $defsThis schema isn’t a plain object with properties — showing the raw JSON instead.
application/json
{
"provider": "together",
"activity": "audio",
"endpointId": "audio/translations",
"kind": "output",
"contentHash": "e21712ec577b544b2fb068db147ca6084724af9fa873b91746705838ca0e77cf",
"specRevision": null,
"provenance": {
"sourceUrl": "https://docs.together.ai/openapi.yaml",
"sourceHash": "468edbdc879c48f500ca284270663ccc30cd83aee57a4e6a4e7a5bc04603b543",
"fetchedAt": 1786771359,
"extractorVersion": "1",
"derivation": "upstream-spec",
"verifiedAt": null
},
"createdAt": 1786771359,
"supersededAt": null,
"schema": {
"oneOf": [
{
"$ref": "#/$defs/AudioTranslationJsonResponse"
},
{
"$ref": "#/$defs/AudioTranslationVerboseJsonResponse"
}
],
"$defs": {
"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!"
}
}
},
"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"
}
}
},
"AudioTranslationJsonResponse": {
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "The translated text",
"example": "Hello, world!"
}
}
},
"AudioTranslationVerboseJsonResponse": {
"type": "object",
"required": [
"language",
"duration",
"text",
"segments"
],
"properties": {
"language": {
"type": "string",
"description": "The target language of the translation",
"example": "english"
},
"duration": {
"type": "number",
"description": "The duration of the audio in seconds",
"example": 3.5
},
"text": {
"type": "string",
"description": "The translated text",
"example": "Hello, world!"
},
"segments": {
"type": "array",
"items": {
"$ref": "#/$defs/AudioTranscriptionSegment"
},
"description": "Array of translation segments"
},
"words": {
"type": "array",
"items": {
"$ref": "#/$defs/AudioTranscriptionWord"
},
"description": "Array of translation words (only when timestamp_granularities includes 'word')"
}
}
}
}
}
}Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"together","endpointId":"audio/translations","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}