Module audio

Module for audio processing, including transcription, translation, and speech synthesis. This module defines the structures and methods for handling audio-based requests and responses. It includes functionality for audio transcription, translation, and speech synthesis. The module facilitates the creation, serialization, and deserialization of requests and responses related to these audio operations.

Features include:

• AudioTranscriptionRequest: Handles requests for audio file transcription using specified models.
• AudioTranscriptionResponse: Returns the transcription text along with optional headers.
• AudioTranslationRequest: Manages requests for translating audio content using specific models.
• AudioTranslationResponse: Delivers translated text and optional response headers.
• AudioSpeechRequest: Manages requests for generating speech from text using designated voice models.
• AudioSpeechResponse: Provides the success status of the speech synthesis operation and optional headers.

Constants for model and voice identifiers are also defined to standardize the references used across requests.

Structs

AudioSpeechRequest

Represents a request for text-to-speech synthesis.

AudioSpeechResponse

Represents the response from a text-to-speech synthesis request.

AudioTranscriptionRequest

Represents a request for audio transcription.

AudioTranscriptionResponse

Represents the response from an audio transcription request.

AudioTranslationRequest

Represents a request for audio translation.

AudioTranslationResponse

Represents the response from an audio translation request.

Constants

TTS_1

Constant for the TTS-1 model identifier.

TTS_1_HD

Constant for the TTS-1 HD model identifier.

VOICE_ALLOY

Constant for the Alloy voice model.

VOICE_ECHO

Constant for the Echo voice model.

VOICE_FABLE

Constant for the Fable voice model.

VOICE_NOVA

Constant for the Nova voice model.

VOICE_ONYX

Constant for the Onyx voice model.

VOICE_SHIMMER

Constant for the Shimmer voice model.

WHISPER_1