Loading

All audio models

Voice cloning

Zonos 2

Voice cloning + text-to-speech: clone a voice from a short sample and make it say anything, multilingual.

Price: from $0.05from 2 credits
Model id: zonos2
Output: Audio

The price changes with the length of the audio or video you send. The estimate call returns the exact figure for your input, free.

Try it in the playground Read the docs

API keys come with the Scale and Ultra plans

Example output of Zonos 2

Run it

The smallest request that works: the required fields only.

POST /run

curl https://api.percify.io/v3/playground/v1/run \
  -H "Authorization: Bearer $PERCIFY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "modelId": "zonos2",
    "input": {
      "text": "Guten Tag, ich heisse Markus und arbeite als Berater in Zuerich.",
      "audio": "https://example.com/voice.mp3"
    }
  }'

EstimatePOST /estimate with the same body returns the price and charges nothing.
RunPOST /run returns an id at once, with status processing.
CollectGET /generations/{id}?wait=55 returns the file URLs, or pass a webhook.

Parameters

3 fields in input, required first.

textRequired
string
What the cloned voice should say
audioRequired
URL
Short.mp3/.wav sample of the voice to clone (public https URL)
clean_speaker_backgroundOptional
booleanDefault false
Strip background noise from the reference before cloning

More voice cloning models

$0.25
XTTS-v2
Coqui XTTS-v2: Multilingual Text To Speech Voice Cloning

Ship your first run today

Pick a use case, run it in the playground, copy the call.

Open the console Browse use cases

API keys come with the Scale and Ultra plans

Zonos 2 API | Percify API