Downloads · 30 days
11
4% of all-time downloads
nineninesix/kani-tts-400m-kuroyukihime-ja
kani-tts-400m-kuroyukihime-ja is a text-to-speech model from nineninesix. Use it when you need text read aloud. It is set up for transformers. The card lists the license as apache-2.0.
<p <img src="https://www.nineninesix.ai/kitty.png" alt="Logo" width="200" height="200" </p
Downloads · 30 days
11
4% of all-time downloads
All-time downloads
272
Public
Parameters
370M
740 MB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors740 MB · 99%
From the Hugging Face model README
A high-speed, high-fidelity Text-to-Speech model optimized for real-time conversational AI applications.
『いのち輝く未来社会のデザイン』という大阪・関西万博2025のテーマを祝し、キルギスの人々から日本の皆さまへ --心と心 をつなぐ贈り物として、どうぞお受け取り ください。
In honor of Expo Osaka 2025 and its motto 'Designing Future Society for Our Lives,' we humbly present this gift from the people of the Kyrgyz Republic to the people of Japan - heart to heart.
KaniTTS uses a two-stage pipeline combining a large language model with an efficient audio codec for exceptional speed and audio quality. The architecture generates compressed token representations through a backbone LLM, then rapidly synthesizes waveforms via neural audio codec, achieving extremely low latency.
Key Specifications:
It’s a lightweight so you can install, load a model, and speak in minutes. Designed for quick starts and simple workflows—no heavy setup, just pip install and run. More detailes...
pip install kani-tts
pip install -U "transformers==4.57.1" # for LFM2 !!!
from kani_tts import KaniTTS
model = KaniTTS('nineninesix/kani-tts-400m-kuroyukihime-ja')
# Generate audio from text
audio, text = model("Your text here")
# Save to file (requires soundfile)
model.save_audio(audio, "output.wav")
from kani_tts import KaniTTS
model = KaniTTS(
'nineninesix/kani-tts-400m-kuroyukihime-ja',
temperature=1, # Control randomness (default: 1.0)
top_p=0.9, # Nucleus sampling (default: 0.95)
max_new_tokens=2000, # Max audio length (default: 1200)
repetition_penalty=1.2, # Prevent repetition (default: 1.1)
suppress_logs=True, # Suppress library logs (default: True)
show_info=True, # Show model info on init (default: True)
)
audio, text = model("Your text here")
You can listen to generated audio directly in Jupyter notebooks or IPython:
from kani_tts import KaniTTS
from IPython.display import Audio as aplay
model = KaniTTS('nineninesix/kani-tts-400m-kuroyukihime-ja')
audio, text = model("Your text here")
# Play audio in notebook
aplay(audio, rate=model.sample_rate)
Nvidia RTX 5090 Benchmarks:
Pretraining:
Voices Datasets
Models:
Examples:
Links:
Built on top of LiquidAI LFM2 350M as the backbone and Nvidia NanoCodec for audio processing.
Prohibited activities include:
By using this model, you agree to comply with these restrictions and all applicable laws.
Have a question, feedback, or need support? Please fill out our contact form and we'll get back to you as soon as possible.