Module oaapi::audio

The audio API of the OpenAI API.

NOTE

This is only available for audio feature flag.

Supported APIs

• Speech
• Transcriptions
• Translations

Supported text response formats

• Plain text
• JSON
• Verbose JSON
• SubRip Subtitle
• WebVTT

Structs

• JsonResponse
  The JSON response.
• JsonResponseFormatter
  The JSON response formatter.
• PlainTextResponseFormatter
  The plain text response formatter.
• SpeechInput
  The input text to speech.
• SpeechRequestBody
  The request body for the /audio/speech endpoint.
• Speed
  The speed to speech.
• SrtResponseFormatter
  The SubRip Subtitle response formatter.
• TranscriptionsRequestBody
  The request body for the /audio/transcriptions endpoint.
• TranslationsRequestBody
  The request boyd for the /audio/translations endpoint.
• VerboseJsonResponse
  The verbose JSON response.
• VerboseJsonResponseFormatter
  The verbose JSON response formatter.
• VttResponseFormatter
  The WebVTT response formatter.

Enums

• AudioApiError
  The error of an audio API calling.
• AudioModel
  The models for audio APIs.
• File
  The audio file to be used for the request.
• Iso639_1
  The ISO 639-1 Language Codes.
• SpeechModel
  The text-to-speech models.
• SpeechResponseFormat
  The response format of a speech audio.
• SpeechStreamError
  The error of a speech stream.
• TextFormatError
  The error of formatting a response text.
• TimestampGranularity
  The timestamp granularity for the result of the transcription.
• Voice
  The voice of a text-to-speech.

Traits

• TextResponseFormat
  A format of a response text.
• TextResponseFormatter
  A formatter of a response text to a specific type: <T>.

Type Aliases

• AudioApiResult
  The result of an audio API calling.
• SpeechStreamResult
  The result of a speech stream.