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

TranslationRequestBuilder

class TranslationRequestBuilder

Constructors

TranslationRequestBuilder

constructor()

Properties

var audio: FileSource?

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

var model: ModelId?

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

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.

var responseFormat: String?

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

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.

Functions

fun build(): TranslationRequest

Builder of TranslationRequest instances.