whatmodel.sh / tts / Kitten TTS Mini 0.8

Kitten TTS Mini 0.8

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Kitten TTS Mini 0.8 is an open-weights text-to-speech model from KittenML, released February 2026. Its published size is 0.08B parameters. Licence: apache-2.0.

Catalogue identity notes

KittenML/kitten-tts-mini-0.8 (80M-parameter ONNX model, about 79 MB). Distinct from the micro and nano 0.8 checkpoints and from KittenTTS 2.

No comparable score yet. No reviewed benchmark results yet.

$ how it compares

Scored text-to-speech models released closest to Kitten TTS Mini 0.8, out of 148 with a score.

#modelscorewhereRAMreleased
4Voxtral TTS (4B) Mistral71±4api $16.00/M chars +local~10GB2026-03
15MiniMax Speech 2.8 Turbo MiniMax66±3api $60.00/M chars2026-02
19MiniMax Speech 2.8 HD MiniMax66±2api $100.00/M chars2026-02
21Eleven v3 ElevenLabs65±1api $100.00/M chars2026-02
101KittenTTS Nano 0.8 KittenML44±5comparison only2026-02

see all text-to-speech models · find the ones that fit your machine

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~0.08 GB · from github.com/KittenML (official)
    pip install kittenml && python -c "from kittenml import KittenTTS; import soundfile as sf; model = KittenTTS('KittenML/kitten-tts-mini-0.8'); audio = model.generate('This high-quality TTS model runs without a GPU.', voice='Jasper'); sf.write('output.wav', audio, 24000)"

Official weights and documentation: huggingface.co/KittenML ↗

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json