Package bg.codexio.ai.openai.api.sdk.voice.transcription

Class Summary

Class	Description
AIModelStage	A stage to choose a model supported by /v1/audio/transcriptions model endpoint compatibility .
AsyncPromiseStage	Registers callbacks and sends request
AsyncPromptStage	Registers user input optionally
AudioFileStage	Configures which audio file to transcribe
FormatStage	Configures the format of the output file
LanguageStage	Tells the OpenAI API in which language the voice in the audio file is.
PreSimplifiedStage	Sets audio file for transcription, before all other autoconfiguration.
ReactivePromptStage	Registers text input optionally
SimplifiedStage	Simplifies configuration with already configured AI Model, temperature, language and output format;
SynchronousPromptStage
TemperatureStage	Configures the temperature or in other words, the creativity of the model.
Transcription	Entrypoint for Transcription API. The interaction starts by configuring the HTTP connection either by providing a preconfigured TranscriptionHttpExecutor http client, HttpExecutorContext, SdkAuth or leave it to Transcription.defaults().
TranscriptionConfigurationStage	Base for all Transcription stages
TranscriptionRuntimeSelectionStage	Configures how the HTTP client to act.