How it works
What this workflow does
Turn approved notes into a short production script an editor can review. An authenticated webhook validates the video brief, asks OpenAI for a hook and three to eight scenes, verifies that every scene cites an exact brief excerpt, estimates narration time, adds the approved call to action verbatim, and writes the result into a Google Doc.
The workflow imports inactive with dryRun: true. Run with sample data uses a fictional 60-second brief and sample script, so the preview does not call OpenAI, Google Docs, or the Data Table.
This is the production-content layer for the Content Publishing, Social Distribution & Newsletter Intelligence blueprint; the Campaign Launch Assurance & Weekly Performance blueprint covers distribution and measurement.
Fit the target runtime
Validate video brief requires a stable request ID, topic, audience, a target between 30 and 180 seconds, approved notes, and a call to action. The model returns a title, a hook, and three to eight scenes. Each scene needs voiceover, a suggested shot, and an evidence quote between 10 and 200 characters that appears exactly in the approved notes.
The workflow counts the hook, scene voiceovers, and supplied CTA, estimates narration at 144 words per minute, and rejects the script if the estimate exceeds the target. The call to action is added verbatim by the workflow, not generated by the model.
Create the review document
Assemble production script builds a plain-text document with the audience, target, estimate, hook, scene-by-scene voiceover and shot suggestions, evidence notes, and the approved CTA. The document title includes the request ID.
The Data Table prevents a serial replay from creating another document. A new request is reserved as doc_pending, a Google Doc is created, the document ID is stored before the content write, and the text is inserted with a batch update. Only after the write is confirmed is the row marked doc_ready.
Validation scope
The supplied report confirms the isolated n8n 2.47.4 import, inactive state, and sample path. It also covers structural checks, the approved CTA, narration-limit rejection, and unsupported scene excerpts. Live OpenAI, Google Docs, and Data Table calls require a staging test with your accounts. The time estimate is a planning aid; pauses, cuts, and visual holds affect the final runtime.
How to use
Before you start
- A current n8n instance with Data Table support.
- An OpenAI API key and a JSON-mode model.
- Google Docs OAuth access for document creation and batch updates.
- A trusted content queue or internal form.
1. Import and run the sample
Download the complete package, extract the ZIP, and read the full setup guide. Import video-script-shot-list.n8n.json and keep it inactive.
Open Run with sample data and choose Test workflow. Assemble production script should return three scenes, the estimated runtime, and the approved CTA.
2. Create the state table
Create an n8n Data Table with text columns event_key, status, detail, and result_id. Enter its ID in Setup. The workflow stores the request ID, draft state, document title, and Google Doc ID.
3. Configure credentials
In Setup, set tableId, the model, and your brandVoice. Add an OpenAI bearer Header Auth credential on Draft with OpenAI. Select Google Docs OAuth on Create Google Doc and Write draft to Google Doc. Put a private inbound Header Auth credential on Receive event.
4. Send a video brief
POST requestId, topic, audience, durationSeconds (30–180), approvedNotes, and callToAction. Use the supplied test payloads to check the brief and expected script. The webhook acknowledges receipt; read the document ID from the Data Table's result_id field.
5. Review and operate
In staging, set dryRun to false and submit the fixture. Read the narration aloud to check pacing and verify that the shot list is feasible. Confirm that the approved CTA appears verbatim and that every scene has a checkable source excerpt.
If a run stops at doc_pending, check the stored document ID or search Drive for the title with the request ID before retrying. Use a new request ID for a deliberate revision.
Related automations
Use the Campaign Image & Caption System for the campaign visual and the Article-to-Social Draft System for channel copy. The Source-Based Checklist System creates a related handout. Read the Content Publishing & Newsletter Intelligence blueprint for the wider production process.