Automate video voiceover & subtitles with Whisper, OpenAI TTS & FFmpeg

Automate Video Editing with AI

Who’s it for This workflow is ideal for content creators, training providers, agencies, and businesses that need to quickly turn raw videos into polished, captioned, or narrated content — without hiring editors or spending hours in manual editing tools.

It’s especially valuable for those who want full freedom of video editing capacity on their own platform instead of relying on costly SaaS tools with heavy limitations, recurring fees, or watermarks. With this template, you get enterprise-grade AI editing self-hosted in your n8n, under your control.

Perfect for: - E-learning & educators producing accessible multilingual lessons - Corporate trainers automating internal tutorials and compliance walkthroughs - Social media teams creating captioned, high-engagement clips - Product teams generating quick demos and explainer videos

---

How it works / What it does This template combines AI transcription, TTS voiceover, and video editing with FFmpeg into a single automated pipeline:

- Voiceover Mode - Transcribes video with OpenAI Whisper - Cleans text using on-screen frames for accuracy - Generates natural AI voiceovers (EN/AR) with OpenAI Speech - Re-times the video to match the narration → synced professional dub

- Subtitle Mode - Merges multiple video clips with FFmpeg - Transcribes or translates audio to generate SRT subtitles - Hardcodes captions directly into the final MP4 (style customizable)