ElevenLabs Scribe Transcription n8n Workflow (99+ Languages)

Turn audio & video into structured text with ElevenLabs Scribe—inside n8n

This ElevenLabs Scribe Transcription n8n workflow converts any audio or video file into structured text using the ElevenLabs Scribe speech-to-text model (supports 99+ languages). Upload a file, run the workflow, and use the output for subtitles, SEO content, accessibility, or more—automated end to end via the ElevenLabs API.

What this workflow does

• Automatically upload your audio/video file into the workflow.
• Transcribe the content with high accuracy using the ElevenLabs Scribe model (scribe_v1).
• Export structured text that you can feed into downstream tasks such as summaries, subtitles, or content generation.

The workflow is designed to integrate seamlessly with n8n so you can reliably convert speech to text without manual copy/paste.

Use cases

• Podcast transcriptions: convert episodes into blog-ready text for SEO and accessibility.
• YouTube subtitles: generate captions automatically to improve engagement.
• Legal & compliance: transcribe meetings, interviews, or customer calls into accurate text records.
• E-learning: turn lectures and webinars into structured course notes.
• SEO & content marketing: repurpose video speech into articles, quotes, and social content.

Technical details

• n8n integration using:
  • HTTP Request node to call the ElevenLabs Scribe API
  • Manual Trigger to start the transcription run
  • Read/Write File nodes to handle your input/output files

Best speech-to-text results start with the ElevenLabs Scribe model—try the model here: ElevenLabs Scribe.