Inheritance diagram for FAudioBase:

Public Attributes
FString	File

FString	Model {"whisper-1"}

FString	Prompt

FString	Response_Format {"json"}

float	Temperature {0.0f}

Member Data Documentation

◆ File

FString FAudioBase::File

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

◆ Model

FString FAudioBase::Model {"whisper-1"}

ID of the model to use. Only whisper-1 (which is powered by our open source Whisper V2 model) is currently available.

◆ Prompt

FString FAudioBase::Prompt

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

◆ Response_Format

FString FAudioBase::Response_Format {"json"}

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

◆ Temperature

float FAudioBase::Temperature {0.0f}

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.

The documentation for this struct was generated from the following file: