Or jump from this list on a smaller screen.

This is a page from the Audivra documentation. Developer exportsindex: http://127.0.0.1:3000/docs/llms.txt, full corpus: http://127.0.0.1:3000/docs/llms-full.txt, OpenAPI: http://127.0.0.1:3000/docs/openapi.json, Postman: http://127.0.0.1:3000/docs/postman.json. Press ⌘K to search docs.

Voice remix

Create a new custom voice from a clone you own using a natural-language prompt.

POST
/api/v1/voices/{id}/remix
Auth required

JSON body with prompt (8–500 characters). The parent clone must be ready and owned by you. Remix consumes one custom voice slot.

Parameters

NameTypeRequiredDescription
idstringYesParent clone UUID (path)
promptstringYesHow to change the voice — tone, pacing, accent
namestringNoDisplay name for the remix

Request body

JSON
{
  "prompt": "Slightly deeper and slower — like a late-night radio host.",
  "name": "Founder voice — warmer"
}

Response

JSON
{
  "clone": { "id": "8c1a…", "status": "queued", "source": "remix" },
  "voice_id": "8c1a…",
  "parent_id": "3f2c…",
  "poll": "/api/voices/clone"
}

Errors

StatusMeaning
401Missing session or API key
402No custom voice slot remaining
404Parent clone not found
409Parent clone is not ready

How remixing works

The parent clone must be ready and owned by you. Remix applies prompt DSP, then a neural restyle when GPU weights are installed, creates a new clone (source=remix), and leaves the original unchanged. Production fails closed without weights.

Studio: /app/voices → Remix tab. Concept: Voice remix.