Models and configuration

Models

ID	Parameters	Approx download
nano-int8	15M	25 MB
nano	15M	56 MB
micro	40M	41 MB
mini	80M	80 MB

Voices

bella, jasper, luna, bruno, rosie, hugo, kiki, and leo.

Full configuration example

const config = KittenTTSConfig(
  // Generation defaults can still be overridden per call.
  model: 'nano-int8',
  defaultVoice: 'luna',
  speed: 1.05,
  downloadRetries: 4,
  ortNumThreads: 4,
  // Bound sentence-group size for long-text inference.
  maxTokensPerChunk: 400,
  trimTrailingSilence: true,
  silenceThreshold: 0.005,
  maxSilenceTrimMs: 250,
  // Disable anonymous SDK analytics when your deployment requires it.
  analytics: false,
);

Option	Default	Purpose
storageDirectory	Application Support; KittenTTS on web	Cache root
modelBaseUrl	Hugging Face	Asset mirror
modelFiles	none	Explicit native or web assets
downloadRetries	4	Total attempts per file
ortNumThreads	4	ONNX Runtime threads
maxTokensPerChunk	400	Long-text inference size
trimTrailingSilence	true	Trim chunk tails
phonemizer	CEPhonemizer	Custom G2P implementation
analytics	true	Anonymous generation metadata

User speed is clamped to 0.5–2.0.