Create voiceover MP3s and karaoke subtitles using Edge TTS and FFmpeg

by Faceless Channel OS ✓ · 73 views · created 2026-07-17 · Content Creation, Multimodal AI

What this workflow does

This workflow has 11 nodes and runs when someone submits an n8n form (“Text to voiceover + karaoke subtitles”). It uses only n8n's built-in nodes.

How it runs

Trigger: When someone submits an n8n form (“Text to voiceover + karaoke subtitles”).

1. Pick the Edge TTS voice (Code): runs custom JavaScript code
2. Prepare file paths for this run (Code): runs custom JavaScript code
3. Create the temp folder (Execute Command): runs a shell command on the n8n host
4. Turn the text into a file (Code): runs custom JavaScript code
5. Save the text file (Read/Write Files from Disk): writes a file to disk
6. Speak the text with Edge TTS (Execute Command): runs a shell command on the n8n host
7. Measure duration and find the pauses (Execute Command): runs a shell command on the n8n host
8. Build word timings from the speech (Code): runs custom JavaScript code
9. Build the karaoke subtitle (Code): runs custom JavaScript code
10. Save the subtitle file (Read/Write Files from Disk): writes a file to disk

Before you upgrade to n8n 3.0

Nodes used (4)

• n8n Form Triggern8n-nodes-base.formTrigger
• Coden8n-nodes-base.code
• Execute Commandn8n-nodes-base.executeCommand
• Read/Write Files from Diskn8n-nodes-base.readWriteFile

From the author

Quick overview This self-hosted workflow takes text and a selected language from an n8n form, generates an MP3 voiceover using the Edge TTS CLI, analyzes the audio with FFmpeg/FFprobe to detect real pauses, and outputs a matching .ass karaoke subtitle file…

View the original on n8n.io → Check your own copy