Interface TranscriptionCreateParams<ResponseFormat>

interface TranscriptionCreateParams<ResponseFormat> {
    file: Uploadable;
    language?: string;
    model: string & {} | "whisper-1";
    prompt?: string;
    response_format?: ResponseFormat;
    temperature?: number;
    timestamp_granularities?: ("word" | "segment")[];
}

Type Parameters

Properties

file language? model prompt? response_format? temperature? timestamp_granularities?

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.

Optionallanguage

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 (which is powered by our open source Whisper V2 model) is currently available.

Optionalprompt

prompt?: string

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

Optionalresponse_format

response_format?: ResponseFormat

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

Optionaltemperature

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.

Optionaltimestamp_granularities

timestamp_granularities?: ("word" | "segment")[]

The timestamp granularities to populate for this transcription. response_format must be set verbose_json to use timestamp granularities. Either or both of these options are supported: word, or segment. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.

Settings

Member Visibility

On This Page

Properties