Skip to main content

Translate Audio

Translate audio from any language to English text using OpenAI Whisper model.

Common Properties​

  • Name - The custom name of the node.
  • Color - The custom color of the node.
  • Delay Before (sec) - Waits in seconds before executing the node.
  • Delay After (sec) - Waits in seconds after executing node.
  • Continue On Error - Automation will continue regardless of any error. Default: false.

Inputs​

  • Connection Id - Connection identifier from Connect node.
  • Audio File - Path to audio file to translate to English. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm, flac, ogg.
  • Use Robomotion AI Credits - Use Robomotion credits instead of your own API key.

Options​

  • Model - Translation model (only Whisper-1 available).
  • Prompt - Optional prompt to guide translation style.
  • Temperature - Sampling temperature (0-1). Default: 0.
  • Timeout (seconds) - Request timeout. Default: 120.
  • Include Raw Response - Include full response with segments. Default: false.

Outputs​

  • Text - Translated text in English.
  • Raw Response - Full response with segments (when enabled).

How It Works​

Translates speech from any language to English:

  1. Validates connection and audio file
  2. Uploads audio to OpenAI
  3. Detects source language automatically
  4. Transcribes and translates to English
  5. Returns English text

Usage Examples​

Example 1: Translate Spanish to English​

Input:
- Audio File: "C:/audio/spanish_recording.mp3"

Output:
- Text: "Hello, welcome to our service. How can I help you today?"

Example 2: With Style Prompt​

Input:
- Audio File: "C:/audio/french_interview.wav"
- Prompt: "Formal business translation"

Output:
- Text: Professionally translated English text

Requirements​

  • Connection Id from Connect node
  • Valid audio file in supported format
  • Audio must contain speech (not just music or silence)

Tips for RPA Developers​

  • Automatic Detection: No need to specify source language - model detects it automatically
  • English Only: This node only outputs English. For other target languages, use Generate Text with translation prompts.
  • vs Transcribe: Use Translate for foreign language to English. Use Transcribe to keep original language.
  • Quality: Works best with clear audio and minimal background noise

Common Errors​

"Audio File cannot be empty"

  • Provide a path to an audio file

"Audio file does not exist"

  • Verify the file path is correct