Short answer: Drop the "Synthesia → Create AI Video" action anywhere in your workflow, map the inputs from upstream nodes, and publish.
Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.
| Field | Type | Required | Description |
|---|---|---|---|
Title title | string | Optional | Video title |
Script script_text | string | Required | What the avatar should say |
Avatar ID avatar | string | Optional | Synthesia avatar id (call list-avatars to find more) |
Background background | string | Optional | Background id or color |
Voice ID voice | string | Optional | Voice id (auto if blank) |
Test Mode test | options | Optional | Test Mode. Options: Yes (free, watermarked), No (charged) |
{"title": "Q3 Update","script_text": "{{trigger.script_text}}","avatar": "e.g. anna_costume1_cameraA, james_costume1_cameraA","background": "off_white, green_screen, custom","voice": "leave empty to use default for avatar"}
{"id": "vid-abc123","title": "Q3 Update","status": "in_progress","download": null,"duration": null,"createdAt": 1700000000}
Use these fields in downstream nodes for routing, logging, or error handling.
Any of these apps can fire this action as part of a workflow.
Triggered by anything in the catalog. Free tier available. No credit card.