Skip to main content
Translates audio into English text. This endpoint takes audio in any supported language and outputs the transcription in English.

Request Body

This endpoint accepts multipart/form-data.
file
required
The audio file to translate. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm. Maximum file size is 25MB.
string
required
The model to use for translation (e.g., whisper-1).
string
Optional text to guide the model’s style. Should be in English.
string
default:"json"
The output format. Options: json, text, srt, verbose_json, vtt.
number
default:"0"
Sampling temperature between 0 and 1.

Response

string
The translated English text.

Examples

Basic Translation

With Prompt Guidance

SRT Subtitles in English

Response Example

Supported Languages

The translation endpoint accepts audio in any of the following languages and translates to English:
Unlike transcription, translation always outputs English text regardless of the input language.