Fix: incorrect fields on AudioTranscription for realtime.

[iskng]

Spec input_audio_transcription object

language string

Optional The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.

model string

Optional The model to use for transcription, whisper-1 is the only currently supported model.

prompt string

currently

#[derive(Debug, Serialize, Deserialize, Clone)]
pub struct AudioTranscription {

    /// Whether to enable input audio transcription.
    pub enabled: bool,

    /// The model to use for transcription (e.g., "whisper-1").
    pub model: String,
}