Module audio

Module audio 

Source
Available on crate feature audio-types only.

Structs§

AudioInput
CreateSpeechRequest
CreateSpeechRequestArgs
Builder for CreateSpeechRequest.
CreateSpeechResponse
CreateTranscriptionRequest
CreateTranscriptionRequestArgs
Builder for CreateTranscriptionRequest.
CreateTranscriptionResponseDiarizedJson
CreateTranscriptionResponseJson
Represents a transcription response returned by model, based on the provided input.
CreateTranscriptionResponseVerboseJson
Represents a verbose json transcription response returned by model, based on the provided input.
CreateTranslationRequest
CreateTranslationRequestArgs
Builder for CreateTranslationRequest.
CreateTranslationResponseJson
CreateTranslationResponseVerboseJson
CreateVoiceConsentRequest
Request to create a voice consent recording.
CreateVoiceConsentRequestArgs
Builder for CreateVoiceConsentRequest.
CreateVoiceRequest
Request to create a custom voice.
CreateVoiceRequestArgs
Builder for CreateVoiceRequest.
LogProbProperties
Log probability information for a transcribed token.
SpeechAudioDeltaEvent
SpeechAudioDoneEvent
SpeechUsage
TokenUsageInputTokenDetails
TranscriptTextUsageDuration
TranscriptTextUsageTokens
TranscriptionDiarizedSegment
TranscriptionSegment
TranscriptionTextDeltaEvent
TranscriptionTextDoneEvent
TranscriptionTextSegmentEvent
TranscriptionWord
UpdateVoiceConsentRequest
Request to update a voice consent recording (metadata only).
UpdateVoiceConsentRequestArgs
Builder for UpdateVoiceConsentRequest.
VadConfig
VoiceConsentDeletedResource
The voice consent deletion object.
VoiceConsentListResource
The voice consent list object.
VoiceConsentResource
A consent recording used to authorize creation of a custom voice.
VoiceResource
A custom voice that can be used for audio output.

Enums§

AudioResponseFormat
CreateSpeechResponseStreamEvent
CreateTranscriptionResponseDiarizedJsonTask
CreateTranscriptionResponseStreamEvent
SpeechModel
SpeechResponseFormat
StreamFormat
TimestampGranularity
TranscriptionChunkingStrategy
TranscriptionDiarizedSegmentType
TranscriptionInclude
TranscriptionUsage
TranslationResponseFormat
VadConfigType
Voice

Type Aliases§

SpeechResponseStream_api and non-target_family=wasm
Stream of response events
TranscriptionResponseStream_api and non-target_family=wasm