ActionOpenAIUpdated May 2026

How do I transcribe audio with OpenAI Whisper?

Short answer: Drop the "OpenAI → Transcribe Audio (Whisper)" action anywhere in your workflow, map the inputs from upstream nodes, and publish.

Use this action All 16 OpenAI actions

Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

Field	Type	Required	Description
Audio File URL file_url	string	Required	Public URL of the audio file to transcribe (mp3, mp4, mpeg, mpga, m4a, wav, webm)
Model model	options	Required	Model. Options: Whisper v1
Language language	options	Optional	Language of the audio (improves accuracy). Leave empty for auto-detect.
Prompt prompt	string	Optional	Optional text to guide the model's style or continue a previous segment
Response Format response_format	options	Optional	Response Format. Options: JSON, Plain Text, SRT (subtitles), VTT (subtitles), Verbose JSON (with timestamps)

Sample request

{
  "file_url": "https://example.com/audio.mp3",
  "model": "{{trigger.model}}",
  "language": "{{trigger.language}}",
  "prompt": "e.g. Technical discussion about cloud computing",
  "response_format": "{{trigger.response_format}}"
}

Returns

{
  "text": "Hello, this is a sample transcription of the audio file."
}

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for Transcribe Audio (Whisper).

Any of these apps can fire this action as part of a workflow.

Google Sheets → OpenAI

2 Google Sheets triggers

HubSpot → OpenAI

18 HubSpot triggers

FAQ

Questions about Transcribe Audio (Whisper).

What does the Transcribe Audio (Whisper) action do in OpenAI?

Transcribes audio into text using OpenAI Whisper. Supports mp3, mp4, mpeg, mpga, m4a, wav, and webm; up to 25 MB per file. Also supports translation to English.

What inputs does Transcribe Audio (Whisper) require?

Required: Audio File URL, Model. Every input accepts a static value or a variable from any upstream node in your workflow.

Can I use dynamic inputs from earlier workflow nodes?

Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.

What happens if OpenAI returns an error?

The workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.

Does Transcribe Audio (Whisper) support batch operations?

Yes. Run Transcribe Audio (Whisper) inside a Loop node to process arrays. Tiny Command handles OpenAI's rate limits automatically so you don't have to throttle manually.

More actions