Struct SpeechToTextRequest

pub struct SpeechToTextRequest {
    pub file: Vec<u8>,
    pub model: Option<String>,
    pub temperature: Option<f64>,
    pub language: Option<String>,
    pub english_text: bool,
    pub prompt: Option<String>,
    pub response_format: Option<String>,
}

Represents a request to the speech-to-text API.

• file: The audio file to be transcribed.
• model: The speech recognition model to use.
• temperature: The temperature parameter to control the randomness of the transcription.
• language: The language of the audio file.
• english_text: If true, the API will use the translation endpoint instead of the transcription endpoint.
• prompt: An optional prompt to provide context for the transcription.
• response_format: The desired format of the transcription response, either “text” or “json”.

Fields

file: Vec<u8>

model: Option<String>

temperature: Option<f64>

language: Option<String>

english_text: bool

If true, the API will use following path: /audio/translations instead of /audio/transcriptions

prompt: Option<String>

response_format: Option<String>

Implementations

impl SpeechToTextRequest

Constructs a new SpeechToTextRequest with the given audio file.

Arguments

• file - The audio file to be transcribed.

Returns

A new SpeechToTextRequest instance with the given audio file and default values for other fields.

pub fn new(file: Vec<u8>) -> Self

pub fn temperature(self, temperature: f64) -> Self

Sets the temperature parameter for the speech recognition model.

Arguments

• temperature - The temperature parameter to control the randomness of the transcription.

Returns

The modified SpeechToTextRequest instance with the updated temperature.

pub fn language(self, language: &str) -> Self

Sets the language of the audio file.

Arguments

• language - The language of the audio file.

Returns

The modified SpeechToTextRequest instance with the updated language.

pub fn english_text(self, english_text: bool) -> Self

Sets whether the API should use the translation endpoint instead of the transcription endpoint.

Arguments

• english_text - If true, the API will use the translation endpoint.

Returns

The modified SpeechToTextRequest instance with the updated english_text flag.

pub fn model(self, model: &str) -> Self

Sets the speech recognition model to use.

Arguments

• model - The speech recognition model to use.

Returns

The modified SpeechToTextRequest instance with the updated model.

pub fn prompt(self, prompt: &str) -> Self

Sets the prompt to provide context for the transcription.

Arguments

• prompt - The prompt to provide context for the transcription.

Returns

The modified SpeechToTextRequest instance with the updated prompt.

pub fn response_format(self, response_format: &str) -> Self

Sets the desired format of the transcription response.

Arguments

• response_format - The desired format of the transcription response, either “text” or “json”.

Returns

The modified SpeechToTextRequest instance with the updated response format.

Trait Implementations

impl Clone for SpeechToTextRequest

fn clone(&self) -> SpeechToTextRequest

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for SpeechToTextRequest

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

Formats the value using the given formatter.