audio

List every voice you can synthesize with

Flat and unpaginated — cache it (5 minutes is a sensible TTL). Every entry always carries id, model and language. Includes your own custom voices alongside the public catalogue.

get/v1/audio/voices

Request

  • Base URL: https://api.ditto.audio (the document declares no server; this is the origin it was published from)
  • URL: https://api.ditto.audio/v1/audio/voices
  • Auth: HTTP bearer

Query parameters

languagestring

Only the voices that can SPEAK this language: every voice of a model that speaks it (one XTTS voice speaks every XTTS language), each marked nativeAccent, native accents first. The reply then also carries language {code, name, withheld?}: a recognised language no model speaks yet lists no voice and says why. Normalized like POST speech; one we cannot place is a 400.

Headers

if-none-matchstring required

Response

Example response

{
  "voices": [
    {
      "id": "kokoro-af-heart",
      "language": "en-us",
      "name": "Heart"
    }
  ],
  "language": {
    "code": "de",
    "name": "German"
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.