ElevenLabsEleven Voice Design
Multilingual Voice Design v2
Multilingual Voice Design v2 creates voice previews from a description. The API exposes it as a separate choice alongside v3.
Preview before saving
The endpoint accepts a voice description and preview text. It returns generated preview IDs, which are then used to create saved voices. Stronger guidance follows the description more closely but can make the result less natural.ElevenLabs Voice Design API
Practical guidance. Set the model ID explicitly when comparing generations. The default of a general endpoint does not necessarily identify the newest model.ElevenLabs Voice Design API
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | eleven_multilingual_ttv_v2 |
| API default | The Voice Design endpoint currently defaults to this modelElevenLabs Voice Design API |
| Languages | 29ElevenLabs model catalog and deprecations |
Related models
- Voice Design v3
ElevenLabs · Eleven Voice Design
Prompted voice-design model that creates and remixes synthetic voice profiles.
Launch date API · Provider product