Module request 

OpenAI Audio API Request Module

This module provides the functionality to interact with the OpenAI Audio API. It supports text-to-speech (TTS), transcription, and translation.

Key Features

• Text-to-Speech: Convert text to natural-sounding audio
• Transcription: Convert audio to text (speech-to-text)
• Translation: Translate audio to English text

Quick Start

use openai_tools::audio::request::{Audio, TtsOptions, Voice};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let audio = Audio::new()?;

    // Generate speech from text
    let options = TtsOptions::default();
    let audio_bytes = audio.text_to_speech("Hello, world!", options).await?;
    std::fs::write("output.mp3", audio_bytes)?;

    Ok(())
}

Structs

Audio

Client for interacting with the OpenAI Audio API.

TranscribeOptions

Options for audio transcription.

TranslateOptions

Options for audio translation.

TtsOptions

Options for text-to-speech generation.

Enums

AudioFormat

Audio output formats for TTS.

SttModel

Speech-to-text models for transcription and translation.

TimestampGranularity

Timestamp granularity options.

TranscriptionFormat

Transcription response formats.

TtsModel

Text-to-speech models.

Voice

Voice options for text-to-speech.