Skip to main content
POST /v1/voice-clones
Clones a voice from your audio clips, so a Digital Human can speak in it. Send up to 25 clips in files.
  • The clone speaks any language. language only sets the language of its preview clip.
  • gender sets grammatical gender in languages that have it.
  • The clone belongs to your workspace. Only Digital Humans and personas in that workspace can use it.
The response has voice_id, catalog_voice_id, name, gender and created_at_unix. Pass catalog_voice_id as voice_id on a Digital Human or persona, or pass voice_id as custom_voice_id. The other voice clone endpoints take voice_id in the path. Rate limit: 100 requests per minute.

Headers

Request body

Send the body as multipart/form-data.

Response

The response is object.

Status codes

Example request

Example response

200
Last modified on November 21, 2026