Skip to main content

Module audio

Module audio 

Source
Expand description

OpenAI Audio wire models.

The local Speech page documents its JSON request but not the SSE event payloads. The Transcription and Translation pages document responses and multipart examples but omit a complete body-parameter table; request-only fields not visible there are retained from the v2 public protocol model.

Structs§

AudioDurationUsage
AudioInputTokenDetails
AudioTokenUsage
CustomVoice
ServerVadConfig
SpeechEvent
SpeechRequest
Transcription
TranscriptionDiarized
TranscriptionDiarizedSegment
TranscriptionLanguage
TranscriptionLogprob
TranscriptionRequest
TranscriptionSegment
TranscriptionTextDeltaEvent
TranscriptionTextDoneEvent
TranscriptionTextSegmentEvent
TranscriptionVerbose
TranscriptionWord
Translation
TranslationRequest
TranslationVerbose
UnknownTranscriptionStreamEvent

Enums§

AudioChunkingAuto
AudioChunkingStrategy
AudioDurationUsageType
AudioTokenUsageType
AudioUsage
KnownSpeechResponseFormat
KnownSpeechStreamFormat
KnownTimestampGranularity
KnownTranscriptionInclude
KnownTranscriptionResponseFormat
KnownTranslationResponseFormat
ServerVadType
SpeechResponseFormat
SpeechStreamEvent
Speech SSE payload observed by compatible backends. The OpenAI snapshot confirms SSE transport but does not name its events; type, delta, and audio are session-derived aliases and every other field remains opaque.
SpeechStreamFormat
SpeechVoice
TimestampGranularity
TranscriptionInclude
TranscriptionResponse
TranscriptionResponseFormat
TranscriptionSegmentType
TranscriptionStreamEvent
TranscriptionTextDeltaType
TranscriptionTextDoneType
TranscriptionTextSegmentType
TranslationResponse
TranslationResponseFormat

Type Aliases§

SpeechResponse
Binary bytes returned when speech uses stream_format: "audio".