AudioCapabilitySection

Snake-case speech metadata exposed by the models API.

kind object

Speech serving kind declared by the card: tts or stt.

anyOf

• string
• null

string

default_response_format object

Default encoded audio response format for TTS requests.

anyOf

• string
• null

string

response_formatsstring[]

Encoded audio response formats declared for TTS requests.

supports_streaming object

Whether the card declares streaming speech support after runtime validation.

anyOf

• boolean
• null

boolean

supports_realtime object

Whether the model declares realtime audio session support.

anyOf

• boolean
• null

boolean

supports_voice_listing object

Whether the model declares voice-listing support.

anyOf

• boolean
• null

boolean

default_voice object

Stable voice used when a request omits an explicit voice.

anyOf

• string
• null

string

voicesstring[]

Stable built-in or bundled-reference voice identifiers.

supports_reference_audio object

Whether the model accepts managed reference audio.

anyOf

• boolean
• null

boolean

supports_translation object

Whether the model declares speech translation support.

anyOf

• boolean
• null

boolean

sample_ratesinteger[]

Declared input or output sample rates in hertz.

AudioCapabilitySection

{
  "kind": "string",
  "default_response_format": "string",
  "response_formats": [
    "string"
  ],
  "supports_streaming": true,
  "supports_realtime": true,
  "supports_voice_listing": true,
  "default_voice": "string",
  "voices": [
    "string"
  ],
  "supports_reference_audio": true,
  "supports_translation": true,
  "sample_rates": [
    0
  ]
}