Transcribe audio in an n8n workflow

Four standard nodes — HTTP Request, Wait, HTTP Request, IF. No community node to install and no code. The same pattern works in Make, Zapier webhooks or any tool that can send an HTTP request.

Your first transcription is free · then 5 minutes a month · no card

The nodes

HTTP Request — POST https://api.audiotranscribr.com/v1/transcriptions, header x-api-key, JSON body {"url": "{{ $json.mediaUrl }}"}. Returns an id.
Wait — 5 seconds.
HTTP Request — GET https://api.audiotranscribr.com/v1/transcriptions/{{ id }} with the same header.
IF — when status is completed (or failed) continue; otherwise loop back to Wait.
HTTP Request — GET {{ $json.results.txt }} to pull the transcript text into the workflow. Use results.srt, results.vtt, results.pdf or results.json for the other files.

What the status node returns

json

{
  "id": "tr_…",
  "status": "completed",
  "duration_seconds": 4572.6,
  "language": "en",
  "results": {
    "json": "https://…", "srt": "https://…", "vtt": "https://…",
    "txt": "https://…", "pdf": "https://…"
  }
}

The result links are valid for an hour and need no authentication, so you can pass them straight to the next node — an email, a Google Drive upload, an LLM prompt.

Ideas

New file in a Drive or S3 folder → transcript PDF emailed to the team.
New podcast episode in an RSS feed → show notes drafted from the transcript.
New video upload → SRT and VTT captions attached to the CMS entry.

Import the workflow

Download n8n-transcribe-url.workflow.json, choose Import from file in n8n, and put your API key in the two HTTP Request nodes.

Pricing

Your first transcription is free, then 5 minutes a month. Paid plans start at $9 a month for 10 hours of audio. All plans →