- Integrations
- /
- D-ID
- /
- Actions
- /
- Create Talk (Custom Avatar)
ActionD-IDUpdated May 2026
How do I create a D-ID talking-head video?
Short answer: Drop the "D-ID → Create Talk (Custom Avatar)" action anywhere in your workflow, map the inputs from upstream nodes, and publish.
Inputs
The fields this action accepts.
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 |
Sample request
{"source_url": "https://example.com/face.jpg","input_text": "{{trigger.input_text}}","voice_id": "{{trigger.voice_id}}","voice_provider": "{{trigger.voice_provider}}"}
Returns
{"id": "tlk_abc","status": "created","created_at": "2026-05-10T10:00:00Z"}
Use these fields in downstream nodes for routing, logging, or error handling.
Triggered by
Apps that pair well as the trigger for Create Talk (Custom Avatar).
Any of these apps can fire this action as part of a workflow.
FAQ
Questions about Create Talk (Custom Avatar).
What does the Create Talk (Custom Avatar) action do in D-ID?
Generates a video of a specific source photo speaking the provided script (text-to-speech voice + lip-sync to the photo). For "personalised greeting from this specific person's photo" use cases.
What inputs does Create Talk (Custom Avatar) require?
Required: Source Image URL, Script. Every input accepts a static value or a variable from any upstream node in your workflow.
Can I use dynamic inputs from earlier workflow nodes?
Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.
What happens if D-ID returns an error?
The workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.
Does Create Talk (Custom Avatar) support batch operations?
Yes. Run Create Talk (Custom Avatar) inside a Loop node to process arrays. Tiny Command handles D-ID's rate limits automatically so you don't have to throttle manually.
More actions
Other D-ID actions.
Action
Create Clip (Presenter)
Generates a video using one of D-ID's pre-recorded presenter avatars speaking your script. Use for production-quality marketing where the natural presenter movement matters more than the specific face.
ActionGet Clip Result
Polls the clip ID for status; returns the result video URL once status is done. For production, configure D-ID's webhook on the generation request to skip polling.
ActionGet D-ID Credit Balance
Returns the remaining credit balance. Useful for pre-flight checks on large batches to avoid mid-batch starvation when generating many videos.
ActionGet Talk Result
Polls the talk ID until status=done; returns the result_url for the rendered MP4. Result URLs expire after a few hours; download or re-host promptly if needed long-term.
ActionList Presenters
Returns stock and custom presenters (if you've trained any). Useful for resolving presenter IDs at workflow-build time when designing template-driven video generation.
Send create talk (custom avatar) from your workflows.
Triggered by anything in the catalog. Free tier available. No credit card.