Jump to section

Or jump from this list on a smaller screen.

This is a page from the Audivra documentation. Developer exports — index: 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 cloning

Instant (short samples) or professional (multi-sample) custom voices on paid plans.

Custom voice slots

Each voice clone you create consumes one custom voice slot on your plan. Deleting a clone frees the slot. Preset library voices do not use slots.

Instant cloning requires Starter or above. Professional multi-sample cloning requires Creator Pro or Developer. Free tier cannot create clones.

Starter: 1 custom voice slot · instant only
Creator: 3 slots · instant + professional
Developer: 10 slots · instant + professional
Free: cloning not available

Clone creation uses a slot — not credits. TTS and video generation with a ready clone consume credits like any other voice.

POST

/api/voices/clone

Auth required

Multipart upload. Instant: 1–5 WAV/MP3 samples (5–10s each). Professional (Creator+): 5–25 files covering 2–30 minutes. Pass kind=professional and consent=true (stores a versioned consent record). Bearer sk_live_… or dashboard session.

Parameters

Name	Type	Required	Description
name	string	No	Display name for the clone
kind	string	No	instant (default) or professional
sample / samples	file	Yes	Audio samples (WAV/MP3). Instant: under 8 MB each. Professional: under 32 MB each.
engine	string	No	f5-tts (default) or xtts-v2
consent	boolean	Yes	Must be true — stores a versioned voice-consent record
language	string	No	ISO language code (default: en)
webhook_url	string	No	Optional POST URL for clone.ready / clone.failed (falls back to dashboard default)

Response

JSON

{
  "clone": {
    "id": "3f2c9a1e-…",
    "name": "Founder voice",
    "status": "queued",
    "kind": "instant",
    "engine": "f5-tts"
  },
  "voice_id": "3f2c9a1e-…",
  "kind": "instant",
  "samples_uploaded": 2,
  "poll": "/api/voices/clone"
}

Errors

Status	Meaning
401	Missing session or API key
402	Free plan, slot limit, or professional cloning not on this tier

Use the clone as voice_id

When status is ready, pass the clone UUID as voice_id to TTS and the unified generate API. Ready clones also appear in GET /api/v1/voices.

curl -X POST /api/v1/tts \
  -H "Authorization: Bearer sk_live_…" \
  -d '{"text":"Hello from my clone","voice_id":"<clone uuid>","model":"f5-tts"}' \
  --output speech.wav

GET /api/voices/clone

List your voice clones, kind, progress, and training status.

PATCH /api/voices/clone/{id}

Rename a clone you own. The voice_id stays the same. Preview the training sample with GET /api/v1/voices/clone/{id}/sample.

DELETE /api/voices/clone/{id}

Delete a clone and free a custom voice slot. Removes stored samples, speaker artifacts, and marketplace listings.

Clone webhooks

Pass webhook_url on upload or set a default in Settings. Audivra POSTs clone.ready or clone.failed once. See Webhooks.

Related: Remix · Marketplace · Models.