Struct CreateTranscriptionRequest

pub struct CreateTranscriptionRequest {
    pub file: String,
    pub model: CreateTranscriptionRequest_Model,
    pub language: Option<String>,
    pub prompt: Option<String>,
    pub response_format: Option<AudioResponseFormat>,
    pub temperature: Option<f64>,
    pub include: Option<Vec<TranscriptionInclude>>,
    pub timestamp_granularities: Option<Vec<String>>,
    pub stream: Option<bool>,
}

Fields

file: String

The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

model: CreateTranscriptionRequest_Model

language: Option<String>

The language of the input audio.

prompt: Option<String>

An optional text to guide the model’s style or continue a previous audio segment.

response_format: Option<AudioResponseFormat>

temperature: Option<f64>

The sampling temperature, between 0 and 1.

include: Option<Vec<TranscriptionInclude>>

Additional information to include in the transcription response.

timestamp_granularities: Option<Vec<String>>

The timestamp granularities to populate for this transcription.

stream: Option<bool>

If set to true, the model response data will be streamed to the client as it is generated using server-sent events.

Trait Implementations

impl Clone for CreateTranscriptionRequest

fn clone(&self) -> CreateTranscriptionRequest

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for CreateTranscriptionRequest

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.