Skip to content

Latest commit

 

History

History
10 lines (9 loc) · 1.22 KB

File metadata and controls

10 lines (9 loc) · 1.22 KB

CreateTranslationRequest

Properties

Name Type Description Notes
file kotlin.Array<kotlin.Byte> The audio file to translate, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.
model kotlin.String ID of the model to use. Only `whisper-1` is currently available.
prompt kotlin.String An optional text to guide the model's style or continue a previous audio segment. The prompt should be in English. [optional]
responseFormat kotlin.String The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt. [optional]
temperature java.math.BigDecimal 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. [optional]