OpenAI Audio Translation

Translate audio to English using OpenAI Whisper.

Overview

OpenAI Audio Translation uses the OpenAI Audio Translations API (POST /audio/translations) with Whisper models to translate audio in any supported language into English text. Accepts binary audio input (mp3, mp4, mpeg, mpga, m4a, wav, webm) and returns an English translation in the specified format (json, text, srt, vtt). Unlike the transcriptions endpoint, this always translates to English regardless of the source language.

Category: AI
Tool Name: openai_audio_translation
Version: 1

Appearance: Icon: openai | Color: #10a37f

Node Type

Action (Binary) — handles file/binary data operations

Input / Output

Direction	Port(s)
Input	Input
Output	Output, Error

Credentials

This tool requires OpenAI credentials. See the Credentials Guide for setup instructions.

Parameters

Parameter	Type	Required	Default	Description
Model	options	No	whisper-1	The Whisper model to use for translation.
				Options: whisper-1 (OpenAI Whisper large-v2 model for audio translation to English)
Binary Property Name	string	No	data	The name of the binary property containing the audio file to translate. Names are case-sensitive — see the upstream node’s Binary Data panel for the exact names to use.
Options	collection	No	{}	Optional translation settings — add only the fields you need.
— Response Format	options	No	json	The format of the translation output.
				Options: json (simple JSON with a text field), text (plain text), srt (SubRip subtitles), vtt (WebVTT subtitles)
— Temperature	number	No	0	Sampling temperature (0-1). Higher values make output more random, lower values more deterministic.
— Response Field Name	string	No	translation	The output field name where the translation text will be stored.
Include Input	boolean	No	false	Whether to include the original input item fields in the output alongside the translation.
Max Concurrency	number	No	5	Maximum number of items to process concurrently.

Output Data

One output item per input item. The English text lands on the field named by Response Field Name (translation by default), with model beside it. The rest of the input item JSON is dropped unless Include Input is on; the input audio binary is forwarded unchanged.

{
  "translation": "The English translation of the spoken audio",
  "model": "whisper-1"
}

• With Response Format set to text, srt or vtt, the response field holds the raw string in that format — ready to write straight to a subtitle file.
• The output is always English. To keep the original language, use OpenAI Speech-to-Text instead.

Reference the result downstream by expression, e.g. {{ $json.translation }}.

Usage Examples

• Translate a French audio recording to English text
• Convert a Spanish podcast episode to English
• Translate a German audio file with SRT subtitle output
• Get English text from a Japanese audio message
• Translate non-English audio to English for further processing

Example Configuration

Translate audio arriving on the default binary property:

{
  "type": "openai_audio_translation",
  "parameters": {
    "binaryPropertyName": "data"
  }
}

Produce English WebVTT captions and keep the original fields:

{
  "type": "openai_audio_translation",
  "parameters": {
    "binaryPropertyName": "audio",
    "includeInput": true,
    "options": {
      "responseFormat": "vtt",
      "responseFieldName": "captions"
    }
  }
}

High-throughput translation of a batch of recordings:

{
  "type": "openai_audio_translation",
  "parameters": {
    "binaryPropertyName": "data",
    "maxConcurrency": 20,
    "options": {
      "responseFormat": "text",
      "temperature": 0
    }
  }
}

Error Handling

Mode	Behavior
stop	Halts workflow on first error
continue	Skips failed items, passes successful ones through
errorPort	Routes failed items to Error output port

Tips

OpenAI Audio Translation converts spoken audio in any supported language into English text using OpenAI Whisper models via the Audio Translations API. Use it when your workflow receives multilingual audio files and requires a unified English output for further processing or analysis. It produces an English translation delivered through the main output in json, text, srt, or vtt format, with failures routed to the error output.