Skip to main content
POST
Generates a base64-encoded audio sample for a given voice ID. Use this to let users hear how a voice sounds before assigning it to an agent.

Request Body

string
required
The voice ID to preview. Get available IDs from the List Voices endpoint.
string
Custom text to speak (1–500 characters). If omitted, a default greeting is used.

Response Fields

This endpoint generates previews for Cartesia voice IDs only. Minimax voices are not supported by this endpoint — use the static previewUrl field returned by the List Voices endpoint instead.Voice previews are generated by the upstream TTS provider (Cartesia). In rare cases, the provider may return a 502 or 503 error due to temporary availability issues.