Module audio 

Audio models for text-to-speech, transcription, and translation

Audio Models

Data structures for the OpenAI Audio API including text-to-speech, speech-to-text transcription, and translation endpoints.

This module has been restructured for better organization:

• types - Core types and enums
• requests - Request structures
• responses - Response structures
• builders - Builder patterns
• models - Model constants

Modules

builders

Audio API builders for fluent request creation

models

Audio model constants

requests

Audio API request structures

responses

Audio API response structures

types

Core audio types and enums

Structs

AudioModels

Common audio models

AudioSpeechRequest

Request for text-to-speech audio generation

AudioSpeechResponse

Response from speech generation endpoint

AudioTranscriptionRequest

Request for speech-to-text transcription

AudioTranscriptionResponse

Response from transcription endpoint

AudioTranslationRequest

Request for speech-to-text translation

AudioTranslationResponse

Response from translation endpoint

SpeechBuilder

Builder for creating speech requests

TranscriptionBuilder

Builder for creating transcription requests

TranscriptionSegment

Segment-level transcription data

TranscriptionWord

Word-level transcription data

TranslationBuilder

Builder for creating translation requests

Enums

AudioFormat

Audio output formats

TimestampGranularity

Timestamp granularity for transcriptions

TranscriptionFormat

Transcription output formats

Voice

Available voices for text-to-speech