Short answer: Drop the "D-ID → Create Talk (Custom Avatar)" 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 |
|---|---|---|---|
Source Image URL source_url | string | Required | A fully qualified URL (https://...) for the source image url. |
Script input_text | string | Required | Script (required) |
Voice ID voice_id | string | Optional | Voice ID |
Voice Provider voice_provider | options | Optional | Voice Provider. Options: Microsoft, Amazon, ElevenLabs |
{"source_url": "https://example.com/face.jpg","input_text": "{{trigger.input_text}}","voice_id": "{{trigger.voice_id}}","voice_provider": "{{trigger.voice_provider}}"}
{"id": "tlk_abc","status": "created","created_at": "2026-05-10T10:00:00Z"}
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.