XTTS-v2

Run it

The smallest request that works: the required fields only.

curl https://api.percify.io/v3/playground/v1/run \
  -H "Authorization: Bearer $PERCIFY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "modelId": "xtts-v2",
    "input": {
      "speaker": "https://example.com/input.wav"
    }
  }'

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

Parameters

4 fields in input, required first.

• speakerRequired
  URL

  Original speaker audio (wav, mp3, m4a, ogg, or flv)

• textOptional
  stringDefault Hi there, I'm your new voice clone. Try your best to upload quality audio

  Text to synthesize

• languageOptional
  en, es, fr, de, it, pt, pl, tr, ru, nl, cs, ar, zh, hu, ko, hiDefault en

  Output language for the synthesised speech

• cleanup_voiceOptional
  booleanDefault false

  Whether to apply denoising to the speaker audio (microphone recordings)