n8n Workflow: Transcribe Audio/Video URL to Markdown Notes

Turn any audio/video URL into Markdown transcript notes (with timestamps)

This n8n workflow transcribes audio or video from a URL—YouTube, podcasts, direct MP3/MP4 files, and many more sources—using Apify’s Universal Media Transcriber (Whisper speech-to-text). It then outputs a clean Markdown document containing the full transcript plus timestamped segments for easy reading, searching, and reuse.

What this workflow does

• Manually executes when you run the workflow.
• Sets a mediaUrl pointing to the audio/video you want to transcribe.
• Calls the Apify Media Transcriber (Whisper) API to transcribe the provided URL and retrieve both text and segment metadata.
• Formats the returned transcript and timestamped segments into a Markdown notes output.

You can also adapt the workflow by replacing the manual trigger to automatically transcribe new content as it appears (for example, new podcast episodes or newly available files).

Use cases

• SaaS operations & documentation: Convert recorded product demos or support calls into searchable Markdown notes.
• Podcast & content pipelines: Auto-transcribe new episodes and store the transcript with timestamps.
• Automation engineers: Build repeatable transcription workflows in n8n without requiring an OpenAI key.
• Research & review: Quickly scan where key moments happen using timestamped segments.

Technical details

• n8n nodes: set, code, http request, manual trigger
• Authentication: Create a free Apify account, generate an Apify API token, and set an HTTP Header Auth credential with Authorization: Bearer <your Apify API token>.
• Transcription engine: Apify’s Universal Media Transcriber (Whisper), supporting 90+ languages and billed per audio minute on Apify—no OpenAI key needed.
• Output: Markdown containing the full transcript and timestamped segments.