🎉 ANNOUNCEMENT: New version of KittenTTS is now available to download!
Kitten TTS is an open-source realistic text-to-speech model with just 15 million parameters, designed for lightweight deployment and high-quality voice synthesis.
Currently in developer preview
For custom support - fill this form
Email the creators with any questions : info@stellonlabs.com
- Ultra-lightweight: Model size less than 25MB
- CPU-optimized: Runs without GPU on any device
- High-quality voices: Several premium voice options available
- Fast inference: Optimized for real-time speech synthesis
| Model | Params | Size | Link |
|---|---|---|---|
| kitten-tts-mini | 80M | 80MB | 🤗 KittenML/kitten-tts-mini-0.8 |
| kitten-tts-micro | 40M | 41MB | 🤗 KittenML/kitten-tts-micro-0.8 |
| kitten-tts-nano | 15M | 56MB | 🤗 KittenML/kitten-tts-nano-0.8 |
| kitten-tts-nano-int8 quantized | 15M | 19MB | 🤗 KittenML/kitten-tts-nano-0.8-int8 |
Some users are facing minor issues with the kitten-tts-nano-int8 model. We are looking into it. Please report to us if you face any issues.
final_vid.mp4
pip install https://github.com/KittenML/KittenTTS/releases/download/0.8/kittentts-0.8.0-py3-none-any.whl
from kittentts import KittenTTS
m = KittenTTS("KittenML/kitten-tts-mini-0.8")
audio = m.generate("This high quality TTS model works without a GPU", voice='Jasper' )
# available_voices : ['Bella', 'Jasper', 'Luna', 'Bruno', 'Rosie', 'Hugo', 'Kiki', 'Leo']
# Save the audio
import soundfile as sf
sf.write('output.wav', audio, 24000)
Works literally everywhere. Needs python3.12. We recommend using conda.
- Release a preview model
- Release the fully trained model weights
- Release mobile SDK
- Release web version