Package io.github.stefanbratanov.jvm.openai

Class TranscriptionRequest.Builder

java.lang.Object
io.github.stefanbratanov.jvm.openai.TranscriptionRequest.Builder
Enclosing class:
TranscriptionRequest
public static class TranscriptionRequest.Builder extends Object

  • Constructor Details

    • Builder

      public Builder()

  • Method Details

    • file

      public TranscriptionRequest.Builder file(Path file)
      Parameters:
      file - The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

    • model

      public TranscriptionRequest.Builder model(String model)
      Parameters:
      model - ID of the model to use

    • language

      public TranscriptionRequest.Builder language(String language)
      Parameters:
      language - The language of the input audio. Supplying the input language in ISO-639-1 format will improve accuracy and latency.

    • prompt

      public TranscriptionRequest.Builder prompt(String prompt)
      Parameters:
      prompt - An optional text to guide the model's style or continue a previous audio segment. The prompt should match the audio language.

    • responseFormat

      public TranscriptionRequest.Builder responseFormat(String responseFormat)
      Parameters:
      responseFormat - The format of the transcript output

    • temperature

      public TranscriptionRequest.Builder temperature(double temperature)
      Parameters:
      temperature - 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

      public TranscriptionRequest.Builder timestampGranularities(List<String> timestampGranularities)
      Parameters:
      timestampGranularities - The timestamp granularities to populate for this transcription. Any of these options: word, or segment. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.

    • build

      public TranscriptionRequest build()