Create translation

POST

/v1/audio/translations

Request

Body Params multipart/form-data

file

required

Audio file object (not file name) to be translated in the following formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav or webm.

model

string

required

The model ID to use. Currently only whisper-1 is available.

prompt

string

optional

An optional text used to guide the model's style or continue the previous audio paragraph. The prompt text should be in English.

response_format

string

optional

The format of the translation result can be selected from: json, text, srt, verbose_json or vtt.

temperature

number

optional

Default is 0
Sample temperature, between 0 and 1. A higher value like 0.8 will make the output more random, while a lower value like 0.2 will make it more focused and deterministic. If set to 0, the model will automatically increase the temperature using log probability until a certain threshold is reached.

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST '/v1/audio/translations' \
--form 'file=@""' \
--form 'model=""' \
--form 'prompt=""' \
--form 'response_format=""' \
--form 'temperature=""'

Responses

🟢200success

application/json

Body

text

string

required

Example

{
    "text": "Hello, my name is Wolfgang and I come from Germany. Where are you heading today?"
}

Create a transcript

Chat completion object