GET

/v1/schemas/elevenlabs/audio/v1/text-to-voice/design?kind=output

kind outputactivity audiohash 39e8597b…extracted Jul 6, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.
Source trace
56793d52b38081086c43910ec1916ff4bb286322250511820c239e4f46831396
{
  "fetchedAt": 1783328734,
  "extractorVersion": "1",
  "verifiedAt": null
}

Response body

2 properties · 2 required · 1 $defs
propertytypedescriptionconstraints
previews*VoicePreviewResponseModel[]The previews of the generated voices.
text*stringThe text used to preview the voices.

Types

1 $defs

VoicePreviewResponseModelobject

audio_base_64*stringThe base64 encoded audio of the preview.
generated_voice_id*stringThe ID of the generated voice. Use it to create a voice from the preview.
media_type*stringThe media type of the preview.
duration_secs*numberThe duration of the preview in seconds.
language*stringThe language of the preview.nullable

Validate a payload

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