How to instant voice clone in ElevenLabs

Instant Voice Clone in ElevenLabs — start free

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
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 request

{
  "sample_url": "e.g. https://example.com/voice-sample.mp3",
  "name": "{{trigger.name}}",
  "description": "{{trigger.description}}",
  "labels": "{\"accent\":\"american\",\"age\":\"young\"}"
}

Returns

{
  "voice_id": "voice_abc",
  "requires_verification": false
}

Use these fields in downstream nodes for routing, logging, or error handling.

FAQ

Questions about Instant Voice Clone.

What does the Instant Voice Clone action do in ElevenLabs?

Trains a custom voice from a short audio sample (a few minutes ideal). Once trained, the voice ID is usable in Text to Speech for consistent narration. For brand-voice or character-voice production at scale.

What inputs does Instant Voice Clone require?

Required: Voice Sample URL, Voice Name. 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 ElevenLabs 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 Instant Voice Clone support batch operations?

Yes. Run Instant Voice Clone inside a Loop node to process arrays. TinyCommand handles ElevenLabs's rate limits automatically so you don't have to throttle manually.

More actions