GET

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

kind outputactivity audiohash f5f50971…extracted Oct 17, 2026version currentsource upstream spec ↗

Response body

6 properties · 5 required · 0 $defs
propertytypedescriptionconstraints
object*enumThe object type, which is always `audio.voice`.audio.voice
id*stringThe voice identifier, which can be referenced in API endpoints.
type*enumHow the voice was created.audio_sample | prompt
name*stringThe name of the voice.
created_at*integerThe Unix timestamp (in seconds) for when the voice was created.format: unixtime
promptstringThe original text prompt used to create the voice. Present for prompt-generated voices with a stored prompt; omitted for audio-sample voices and older voices without a stored 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", …}]}