All models
lightweight

KittenTTS

Apache-2.0

15M params, under 25MB, runs anywhere — even your phone

KittenTTS is an ultra-lightweight English TTS model — around 15 million parameters, small enough to run without a GPU entirely. It trades some expressiveness for extreme efficiency, with a handful of clean preset voices. Via the API it's effectively instant.

Voices

1 voice
Neutral
Defaultdefault
—
NeutralEmotionalNumbers & Dates

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Install

pip install kittentts

KittenTTS FAQ

Do I need a GPU to run KittenTTS?

No — KittenTTS runs in real time on a CPU, no GPU required. It's one of the few open TTS models that does.

Can KittenTTS clone voices?

No — KittenTTS uses preset voices. Browse the voice-cloning category for models that clone from reference audio.

What license is KittenTTS released under?

KittenTTS is released under the Apache-2.0 license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does KittenTTS support?

KittenTTS supports English.

Is there a hosted KittenTTS API?

Yes — OpenSpeech Cloud is launching hosted, pay-per-minute access to KittenTTS and every other model in this directory. No CUDA, Docker, or GPU needed.