Short answer: Drop the "ElevenLabs → Instant Voice Clone" 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 |
|---|---|---|---|
Voice Sample URL sample_url | string | Required | Public HTTPS URL to a single audio sample (MP3/WAV/M4A) of the voice you want to clone. 1–5 minutes recommended. The executor fetches the URL and uploads as a binary multipart part. |
Voice Name name | string | Required | Voice Name (required) |
Description description | string | Optional | Description |
Labels (JSON) labels | string | Optional | {"accent":"american","age":"young"} |
{"sample_url": "e.g. https://example.com/voice-sample.mp3","name": "{{trigger.name}}","description": "{{trigger.description}}","labels": "{\"accent\":\"american\",\"age\":\"young\"}"}
{"voice_id": "voice_abc","requires_verification": false}
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.