Find model-specific speech examples

GET /v1/audio/speech/examples

Returns model-specific speech examples with applicability. Discover valid IDs and modes in the unfiltered catalog first; an invalid filter returns 400. Each example carries applicable and reason; only apply examples whose controls your selected model supports.

Guide and examplesSpeech and voice library All endpoints

Parameters

modelstringFilter by model.

modestringFilter by mode, for example voice-design.

languagestringFilter by language, for example en-US.

idstringFilter by example ID.

recipestringFilter by recipe.

Responses

200The example catalog.

schema_versionstring

catalog_versionstring

verified_atstring

resolved_languagestring

modelsobject[]

examplesobject[]

modelstring

modestringFor example emotion-vector, style-control or voice-design.

languagestring

idstring

recipestring

applicableboolean

reasonstring | null

{
  "schema_version": "1",
  "catalog_version": "2026-09-01",
  "verified_at": "2026-09-01T00:00:00Z",
  "resolved_language": "en-US",
  "models": [
    {
      "id": "openbmb/VoxCPM2"
    }
  ],
  "examples": [
    {
      "model": "openbmb/VoxCPM2",
      "mode": "voice-design",
      "language": "en-US",
      "applicable": true,
      "reason": null
    }
  ]
}

400Invalid request. Fix the request before retrying; use error.code for program logic and error.param to locate the input.

401Invalid or missing API key.

403Host or origin is not allowed, or the license was rejected. Inspect error.code to tell them apart.

503A required local model is still being prepared (model_downloading) or the service is busy (service_busy). Honor Retry-After when present.