Skip to main content
Full schema: POST /v3/voices/clone.
HeyGen instant clones run on the Starfish engine only. The resulting voice works wherever Starfish-compatible voices do — see Text to Speech.
Instant voice cloning creates a usable voice from a single recording in minutes. For a studio-grade clone trained on the HeyGen Voice model, see HeyGen Professional Clone. Instant cloning on third-party voice engines is coming soon.

Quick Example

Response

Request fields

The audio object supports one of these forms:
For local files, upload the recording with the Assets API first and pass the returned asset_id.

Poll clone status

Cloning runs asynchronously. Poll GET /v3/voices/{voice_clone_id} until status is complete:

Use the voice

Once complete, the voice_clone_id works anywhere a voice_id does: pass it to Text to Speech for standalone audio, or to POST /v3/videos to narrate an avatar video. Cloned voices appear in GET /v3/voices with type=private — see Browse Voices.