kitten-tts-mini

The highest quality KittenTTS model at 80M parameters. Best for production applications where output quality is the priority.

kitten-tts-mini is the largest model in the KittenTTS family, delivering the highest quality audio output.

Specifications

Property	Value
Model ID	KittenML/kitten-tts-mini-0.8
Parameters	80M
Size	80 MB
Quality	Highest

When to use this model

• Production applications where audio quality is critical
• Use cases where model size is not a constraint
• Offline or server-side inference with adequate storage
• Scenarios where you are generating a small number of high-value audio clips

Usage

from kittentts import KittenTTS
import soundfile as sf

model = KittenTTS("KittenML/kitten-tts-mini-0.8")
audio = model.generate(
    "Welcome to Kitten TTS, the ultra-lightweight text-to-speech library.",
    voice="Jasper"
)
sf.write("output.wav", audio, 24000)

The model is downloaded from Hugging Face on first use and cached locally. Pass cache_dir to control where it is stored.

Related models

• kitten-tts-micro — 40M params, balanced quality and speed
• kitten-tts-nano — 15M params, fastest inference