GET

/v1/schemas/elevenlabs/audio/v1/text-to-voice

kind inputactivity audiohash 8ff39fc8…extracted Jul 6, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.
Source trace
56793d52b38081086c43910ec1916ff4bb286322250511820c239e4f46831396
{
  "fetchedAt": 1783328734,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

5 properties · 3 required · 0 $defs
propertytypedescriptionconstraints
voice_name*stringName to use for the created voice.
voice_description*stringDescription to use for the created voice.length ≥ 20 · length ≤ 1000
generated_voice_id*stringThe generated_voice_id to create; obtain it from POST /v1/text-to-voice/design, POST /v1/text-to-voice/:voice_id/remix, or the response headers when generating previews.
labelsobjectOptional, metadata to add to the created voice. Defaults to None.nullable
played_not_selected_voice_idsstring[]List of voice ids that the user has played but not selected. Used for RLHF.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","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}