Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.vmeg.ai/llms.txt

Use this file to discover all available pages before exploring further.

Create a reusable cloned voice from sample audio. On success, VMEG assigns a voiceId and stores the clone as an API voice asset.

​
Sync vs async

ModeEndpointResults
SyncPOST /openapi/v1/task/clone-voice/createvoiceId and sample metadata in HTTP response
AsyncPOST /openapi/v1/task/clone-voice/create-asyncWebhook when event is openapi-clone-voice (data.voiceId)
Every create and create-async call requires X-Idempotency-Key. Async also needs a configured Webhook.

​
Workflow

1

Prepare sample

Provide reference audio per request schema (URL or uploaded asset fields in API reference).
2

Submit clone task

Sync or async create endpoint with provider from Supported clone methods and sampleLanguage from Supported languages.
3

Use voiceId

Pass voiceId to Text to speech requests.

​
After cloning

  • List clones: POST /openapi/v1/assets/voice/clone/list
  • Rename: POST /openapi/v1/assets/voice/clone/update
  • Delete: POST /openapi/v1/assets/voice/clone/delete
Clones are only available through API asset endpoints, not among voices you pick on vmeg.ai. See Assets overview. Request and callback schemas: API reference → Voice clone operations.