Interface TranscriptionCreateParams

interface TranscriptionCreateParams {
    file: Uploadable;
    language?: string;
    model: string & {} | "whisper-1";
    prompt?: string;
    response_format?: "json" | "text" | "srt" | "verbose_json" | "vtt";
    temperature?: number;
}

Properties

file language? model prompt? response_format? temperature?

Properties

file

file: Uploadable

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

Optional language

language?: string

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

model

model: string & {} | "whisper-1"

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

Optional prompt

prompt?: string

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

Optional response_format

response_format?: "json" | "text" | "srt" | "verbose_json" | "vtt"

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

Optional temperature

temperature?: number

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.

Settings

Member Visibility

Theme

On This Page

Generated using TypeDoc