openai-core/com.aallam.openai.api.audio/TranscriptionRequestBuilder

TranscriptionRequestBuilder

class TranscriptionRequestBuilder

Constructors

constructor()

Properties

audio

var audio: FileSource?

The audio file to transcribe, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.

language

var language: String?

The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.

model

var model: ModelId?

ID of the model to use. Only whisper-1 is currently available.

prompt

var prompt: String?

An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

responseFormat

var responseFormat: AudioResponseFormat?

The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.

temperature

var temperature: Double?

The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.

timestampGranularities

var timestampGranularities: List<TimestampGranularity>?

The timestamp granularities to populate for this transcription. responseFormat must be set verbose_json to use timestamp granularities. Either or both of these options are supported: word, or segment. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.

Functions

build

fun build(): TranscriptionRequest

Builder of TranscriptionRequest instances.