Struct TranslationsRequestBody 

pub struct TranslationsRequestBody {
    pub file: File,
    pub model: AudioModel,
    pub prompt: Option<Prompt>,
    pub temperature: Option<Temperature>,
}

The request boyd for the /audio/translations endpoint.

Fields

file: File

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: AudioModel

ID of the model to use. Only whisper-1 is currently available.

prompt: Option<Prompt>

An optional text to guide the model’s style or continue a previous audio segment. The prompt should match the audio language.

temperature: Option<Temperature>

The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.

Implementations

impl TranslationsRequestBody

pub fn new( file: File, model: AudioModel, prompt: Option<Prompt>, temperature: Option<Temperature>, ) -> Self

Creates a new TranslationsRequestBody.

Trait Implementations

impl Debug for TranslationsRequestBody

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

Formats the value using the given formatter.

impl Default for TranslationsRequestBody

fn default() -> TranslationsRequestBody

Returns the “default value” for a type.

impl Display for TranslationsRequestBody

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

Formats the value using the given formatter.