KittenML /KittenTTS

Open-source State-of-the-art TTS model which runs on a CPU 😻

★ 16,884⑂ 1,064👁 129⑃ 80● 111▤ 3
PythonApache-2.0Created 2025-08-05
下载:0.8.10.8.1 ↓0.8.12026-02-24
+11
日增长
+100
周增长
+1,046
月增长
16,884
stars
1,064
forks
129
watchers
80
prs
111
issues
3
releases

README

Kitten-TTS


  



  
  
  
  


  New: Free Kitten-TTS 2 API available at  https://platform.kittenml.com

Kitten-TTS is a series of sota open-source text-to-speech models, built by KittenML. Its flagship model, Kitten-TTS 2, is a
1.7B-parameter 1-bit TTS model with in-context voice cloning and expression control. It provides SOTA quality while being so efficient that it runs realtime on CPUs and consumer GPU's!

The library also ships our existing lightweight V0.8 models,
15M-80M parameters, which run on CPU without a GPU. Both families load through the same
KittenTTS(...) constructor.

Commercial support is available. For integration assistance, custom voices, or enterprise licensing, contact us.






 Table of Contents

- Features
- Available Models
- Demo
- Quick Start
- Voice cloning
- Expression controls
- Running on CPU
- Running on a Mac
- Running with vLLM
- Long text and streaming
- Documentation
- System Requirements
- Commercial Support
- Community and Support
- License

 Features

- Voice cloning -- Clone any speaker from 5-30 seconds of audio, no fine-tuning
- 115 built-in voices -- Including the eight from KittenTTS 0.8
- Multilingual -- 20 languages: English, Arabic, Chinese, French, German, Hindi, Italian, Portuguese, Russian, Spanish, Japanese, Korean, Turkish, Dutch, Swedish, Danish, Finnish, Swahili, Greek, Hebrew
- Expression control -- [emotion] tags, inline  tags, and (((emphasis))) spans
- Decoding presets -- Trade stability against expressiveness per request
- Long-form text -- Sentence-aware chunking with seamless joins
- Text preprocessing -- Numbers, currencies, dates, units and abbreviations expanded automatically
- 24 kHz output -- High-quality audio at a standard sample rate
- Runs without a GPU
- Runs real time on a CPU -- Check Running on CPU
- Optimized C++ inference for CPU -- Our fork of llama.cpp
- Several times realtime on Apple silicon -- Check Running on a Mac




 Available Models

KittenTTS 2 -- speech language model:

| Model | Parameters | Size | Voices | Download |
|---|---|---|---|---|
| kitten-tts-2 | 1.7B | 492 MB | 115 + cloning | KittenML/kitten-tts-2 |

KittenTTS 2 nano / pico / mini -- small multilingual models: int8 ONNX for CPU, or the float32 weights in PyTorch (docs):

| Model | Parameters | Size | Languages | Download |
|---|---|---|---|---|
| kitten-tts-2-mini | 82M | ~82 MB | 16 | KittenML/kitten-tts-2-mini |
| kitten-tts-2-nano | 17M | 17 MB per language | 8 | KittenML/kitten-tts-2-nano |
| kitten-tts-2-pico | 7M | 8 MB per language | 8 | KittenML/kitten-tts-2-pico |

python
m = KittenTTS("KittenML/kitten-tts-2-nano")                     ONNX, int8
audio = m.generate("Guten Morgen.", voice="Paul")               a German voice
m = KittenTTS("KittenML/kitten-tts-2-nano", backend="torch")    PyTorch, float32


Lightweight ONNX -- runs on CPU, no GPU required:

| Model | Parameters | Size | Download |
|---|---|---|---|
| kitten-tts-mini | 80M | 80 MB | KittenML/kitten-tts-mini-0.8 |
| kitte

Top issues

Latest release

0.8.1 0.8.1 2026-02-24

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON