Struct SttRequest 

pub struct SttRequest {
    pub model: String,
    pub audio: Vec<u8>,
    pub media_type: String,
    pub language: Option<String>,
}

Parameters for a speech-to-text (transcription) request.

Fields

model: String

STT model identifier (e.g., "whisper-1").

audio: Vec<u8>

Raw audio bytes.

media_type: String

MIME type of the audio (e.g. “audio/mp3”, “audio/wav”).

language: Option<String>

Optional language hint (ISO 639-1, e.g. “en”).