Struct rust_ai::openai::apis::audio::Audio

pub struct Audio {
    pub model: Model,
    pub prompt: Option<String>,
    pub response_format: Option<Format>,
    pub temperature: Option<f32>,
    pub language: Option<Language>,
}

Given a prompt and an instruction, the model will return an edited version of the prompt.

Fields

model: Model

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

prompt: Option<String>

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

response_format: Option<Format>

The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.

temperature: Option<f32>

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.

language: Option<Language>

The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.

Implementations

impl Audio

pub fn set_prompt(&mut self, content: &str)

Set target prompt for image generations.

Arguments

• content - Target prompt

pub async fn transcription( &self, file_name: String, bytes: Vec<u8> ) -> Result<AudioResponse, Box<dyn Error>>

Send transcription request to OpenAI.

The audio file to transcribe, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.

Arguments

• file_name - Audio file name
• bytes - Bytes vector of the file

Examples found in repository

examples/audio-transcription.rs (line 13)

async fn main() -> Result<(), Box<dyn Error>> {
    std::env::set_var("RUST_LOG", "debug");
    std::env::set_var("RUST_BACKTRACE", "1");
    log4rs::init_file("log4rs.yml", Default::default()).unwrap();

    let audio = Audio::default();
    let file_path = PathBuf::from("D:\\Contents\\Downloads\\20220918_000937.m4a");
    let result = audio
        .transcription(String::from("20220918_000937.m4a"), std::fs::read(file_path).unwrap())
        .await?;
    println!("{:?}", result.text);
    Ok(())
}

pub async fn translation( &self, file_name: String, bytes: Vec<u8> ) -> Result<AudioResponse, Box<dyn Error>>

Translates audio into into English.

The audio file to transcribe, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.

Arguments

• file_name - Audio file name
• bytes - Bytes vector of the file

Examples found in repository

examples/audio-translation.rs (line 13)

async fn main() -> Result<(), Box<dyn Error>> {
    std::env::set_var("RUST_LOG", "debug");
    std::env::set_var("RUST_BACKTRACE", "1");
    log4rs::init_file("log4rs.yml", Default::default()).unwrap();

    let audio = Audio::default();
    let file_path = PathBuf::from("D:\\Contents\\Downloads\\20220918_000937.m4a");
    let result = audio
        .translation(String::from("20220918_000937.m4a"), std::fs::read(file_path).unwrap())
        .await?;
    println!("{:?}", result.text);
    Ok(())
}

Trait Implementations

impl Debug for Audio

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

Formats the value using the given formatter.

impl Default for Audio

fn default() -> Self

Returns the “default value” for a type.