Create AI videos from prompts with OpenAI script, TTS & Pexels B-roll assembly
Needs changesWhat this workflow does
This workflow has 13 nodes and runs when an HTTP GET request hits its webhook URL. Along the way it connects Google Drive. It also calls api.pexels.com over HTTP.
How it runs
Trigger: When an HTTP GET request hits its webhook URL.
- Set Video Parameters (Edit Fields (Set)): sets 3 fields: prompt, videoStyle, targetDuration
- Prepare Script Prompt (Edit Fields (Set)): sets 1 field: systemPrompt
- Generate Video Script (OpenAI): uses OpenAI
- Parse Script into Scenes (Code): runs custom JavaScript code
- Generate Voiceover (TTS) (OpenAI): uses OpenAI
- Search Stock Footage (Pexels) (HTTP Request): calls api.pexels.com
- Merge: merges the data from its input branches
- Extract Video URLs (Code): runs custom JavaScript code
- Generate Subtitles (SRT) (Code): runs custom JavaScript code
- Download B-Roll Footage (HTTP Request): calls an HTTP API
…plus 2 more steps. See the full node list below.
Services it uses
HTTP calls to: api.pexels.com
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- OpenAI (legacy) in Generate Video Script, Generate Voiceover (TTS): replace with OpenAI node (AI section).
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| OpenAI (legacy) Generate Video Script, Generate Voiceover (TTS) | OpenAI node (AI section) |
Nodes used (8)
- OpenAI
n8n-nodes-base.openAi - Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Merge
n8n-nodes-base.merge - Execute Command
n8n-nodes-base.executeCommand - Google Drive
n8n-nodes-base.googleDrive - Edit Fields (Set)
n8n-nodes-base.set - Webhook
n8n-nodes-base.webhook
From the author
Automatically creates complete videos from a text prompt—script, voiceover, stock footage, and subtitles all assembled and ready. How it works Send a video topic via webhook (e.g., "Create a 60-second video about morning exercise"). The workflow uses OpenAI…