Available on crate feature
audio-types only.Structs§
- Audio
Input - Create
Speech Request - Create
Speech Request Args - Builder for
CreateSpeechRequest. - Create
Speech Response - Create
Transcription Request - Create
Transcription Request Args - Builder for
CreateTranscriptionRequest. - Create
Transcription Response Diarized Json - Create
Transcription Response Json - Represents a transcription response returned by model, based on the provided input.
- Create
Transcription Response Verbose Json - Represents a verbose json transcription response returned by model, based on the provided input.
- Create
Translation Request - Create
Translation Request Args - Builder for
CreateTranslationRequest. - Create
Translation Response Json - Create
Translation Response Verbose Json - LogProb
Properties - Log probability information for a transcribed token.
- Speech
Audio Delta Event - Speech
Audio Done Event - Speech
Usage - Token
Usage Input Token Details - Transcript
Text Usage Duration - Transcript
Text Usage Tokens - Transcription
Diarized Segment - Transcription
Segment - Transcription
Text Delta Event - Transcription
Text Done Event - Transcription
Text Segment Event - Transcription
Word - VadConfig
Enums§
- Audio
Response Format - Create
Speech Response Stream Event - Create
Transcription Response Diarized Json Task - Create
Transcription Response Stream Event - Speech
Model - Speech
Response Format - Stream
Format - Timestamp
Granularity - Transcription
Chunking Strategy - Transcription
Diarized Segment Type - Transcription
Include - Transcription
Usage - Translation
Response Format - VadConfig
Type - Voice
Type Aliases§
- Speech
Response Stream _api - Stream of response events
- Transcription
Response Stream _api