Skip to main content

Models and voices

Models

Model repositoryParametersApprox sizeGuidance
KittenML/kitten-tts-nano-0.8-int815M25 MBSmallest download; validate output for your use case
KittenML/kitten-tts-nano-0.815M56 MBCompact fp32 default family
KittenML/kitten-tts-micro-0.840M41 MBBalance of quality and footprint
KittenML/kitten-tts-mini-0.880M80 MBHighest-quality v0.8 option
from kittentts import KittenTTS

tts = KittenTTS("KittenML/kitten-tts-micro-0.8")

Passing a name without / automatically uses the KittenML Hugging Face organization.

Voices

Display nameEmbedding IDCharacter
Bellaexpr-voice-2-fWarm and expressive
Jasperexpr-voice-2-mClear and conversational
Lunaexpr-voice-3-fCalm and smooth
Brunoexpr-voice-3-mDeep and steady
Rosieexpr-voice-4-fBright and friendly
Hugoexpr-voice-4-mAuthoritative
Kikiexpr-voice-5-fLively and energetic
Leoexpr-voice-5-mRelaxed and natural

The labels describe intended character, not guaranteed prosody. Evaluate recordings using your own text, punctuation, and speed settings.

Cache location

Hugging Face controls the default cache. Pass cache_dir to keep assets in an application-specific location:

tts = KittenTTS(
"KittenML/kitten-tts-nano-0.8",
cache_dir="./.models",
)