Skip to main content

AudioCardConfig

Optional speech-specific capability declarations for a model card.

kind object

Speech serving kind: tts for text-to-speech or stt for speech-to-text.

anyOf
AudioCardKind (string)

Speech model kind declared by a model card's [audio] section.

Possible values: [tts, stt]

defaultResponseFormat object

Default encoded audio response format for TTS requests.

anyOf
AudioResponseFormat (string)

Audio response formats supported by the speech serving API.

Possible values: [mp3, wav, flac, ogg, opus, pcm]

responseFormatsAudioResponseFormat (string)[]

Encoded audio formats this model can produce for TTS requests.

Possible values: [mp3, wav, flac, ogg, opus, pcm]

Default value: []
supportsStreaming object

Whether a validated Skulk runtime path can stream partial speech or transcripts.

anyOf
boolean
supportsRealtime object

Whether the model exposes a realtime session interface.

anyOf
boolean
supportsVoiceListing object

Whether the model can enumerate voices through a voice-listing API.

anyOf
boolean
voicesstring[]

Stable built-in voice identifiers exposed by the model.

Default value: []
voiceCatalog object[]

Optional display and language metadata for every declared built-in voice.

  • Array [
    • idId (string)required

    Model-specific voice identifier accepted by speech synthesis.

    nameName (string)required

    Human-readable voice name shown by clients.

    preferredLanguagesstring[]

    Ordered BCP 47 language tags for which this voice is a preferred match.

    Default value: []
    referenceProfile object

    Bundled reference profile used to condition models without built-in voices.

    anyOf
    string
  • ]
    • defaultVoice object

    Built-in voice used when a TTS request omits an explicit voice.

    anyOf
    string
    supportsReferenceAudio object

    Whether the model accepts managed reference audio for voice conditioning.

    anyOf
    boolean
    supportsTranslation object

    Whether the model can translate speech instead of only transcribing it.

    anyOf
    boolean
    sampleRatesinteger[]

    Supported output or input sample rates in hertz.

    Possible values: > 0

    Default value: []
    AudioCardConfig
    {
      "kind": "tts",
      "defaultResponseFormat": "mp3",
      "responseFormats": [
        "mp3"
      ],
      "supportsStreaming": true,
      "supportsRealtime": true,
      "supportsVoiceListing": true,
      "voices": [
        "string"
      ],
      "voiceCatalog": [
        {
          "id": "string",
          "name": "string",
          "preferredLanguages": [
            "string"
          ],
          "referenceProfile": "string"
        }
      ],
      "defaultVoice": "string",
      "supportsReferenceAudio": true,
      "supportsTranslation": true,
      "sampleRates": [
        0
      ]
    }