---
title: kani-tts-400m-ky-kani
canonical_url: "https://www.modelscope.ai/models/nineninesix/kani-tts-400m-ky-kani"
md_url: "https://www.modelscope.ai/models/nineninesix/kani-tts-400m-ky-kani.md"
repository: nineninesix/kani-tts-400m-ky-kani
last_updated: 2026-10-29
license: other
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
model_type:
  - lfm2
architectures:
  - Lfm2ForCausalLM
base_model:
  - nineninesix/kani-tts-400m-0.3-pt
base_model_relation: finetune
parameters: 369.8M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - ky
downloads: 30
stars: 0
---

# kani-tts-400m-ky-kani

> kani-tts-400m-ky-kani - An open-source model by nineninesix on ModelScope. 🎙️ Try it online: AkylAI — AI voice studio for Kyrgyz, Kazakh and Russian: text-to-speech, video dubbing, voice cloning and speech-to-text. No install, works in the browser. ·…

nineninesix/kani-tts-400m-ky-kani is a 369.8M-parameter text-to-speech model on ModelScope. licensed under other. derived from nineninesix/kani-tts-400m-0.3-pt.

- **Repository**: nineninesix/kani-tts-400m-ky-kani
- **License**: other
- **Tasks**: text-to-speech
- **Parameters**: 369.8M
- **Base model**: nineninesix/kani-tts-400m-0.3-pt
- **Downloads**: 30
- **Stars**: 0
- **Last updated**: 2026-10-29

Source: https://www.modelscope.ai/models/nineninesix/kani-tts-400m-ky-kani

---

<p>
  <img src="https://cdn-uploads.huggingface.co/production/uploads/64fab67bd268b2f1ad8a826b/Tr9m7BSyfbNLp_2qevxyM.png" alt="Logo" width="200" height="200">
</p>

# KaniTTS Kyrgyz

> 🎙️ **Try it online: [AkylAI](https://akylai.com/)** — AI voice studio for Kyrgyz, Kazakh and Russian: [text-to-speech](https://akylai.com/ky/text-to-speech), [video dubbing](https://akylai.com/ky/video-dubbing), [voice cloning](https://akylai.com/ky/voice-cloning) and [speech-to-text](https://akylai.com/ky/speech-to-text). No install, works in the browser. · [Кыргызча](https://akylai.com/ky/) · [Қазақша](https://akylai.com/kk/) · [Русский](https://akylai.com/ru/)

[![](https://dcbadge.limes.pink/api/server/https://discord.gg/NzP3rjB4SB?style=flat)](https://discord.gg/NzP3rjB4SB) [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)


A high-speed, high-fidelity Text-to-Speech model optimized for real-time conversational AI applications.

## Overview

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:**
- **Model Size:** 400M parameters
- **Sample Rate:** 22kHz
- **Language:** Kyrgyz
- **License:** Apache 2.0

## Performance

**On [NovitaAI](https://novita.ai/) RTX 5090 using vLLM:**
- **RTF:** ~0.2 (5 times faster than realtime)
- **Memory:** 16GB GPU VRAM used
- **Source Code:** https://github.com/nineninesix-ai/kanitts-vllm
  
#### GPU Benchmark Results

| GPU Model | VRAM | Cost ($/hr) | RTF |
|-----------|------|-------------|-----|
| RTX 5090 | 32GB | $0.423 | 0.190 |
| RTX 4080 | 16GB | $0.220 | 0.200 |
| RTX 5060 Ti | 16GB | $0.138 | 0.529 |
| RTX 4060 Ti | 16GB | $0.122 | 0.537 |
| RTX 3060 | 12GB | $0.093 | 0.600 |

*Lower RTF is better (< 1.0 means faster than real-time). Benchmarks conducted on [Vast AI](https://vast.ai/).*

## Quickstart: Install from PyPI & Run Inference

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...](https://pypi.org/project/kani-tts/)

### Install

```bash
pip install kani-tts
pip install -U "transformers==4.57.1" # for LFM2 !!!
```
### Quick Start

```python
from kani_tts import KaniTTS

model = KaniTTS('nineninesix/kani-tts-400m-ky-kani')

# Generate audio from text
audio, text = model("Салам, менин атым Акылай. Бүгүн силерге кандай жардам бере алам?")

# Save to file (requires soundfile)
model.save_audio(audio, "output.wav")
```

### Working with Multi-Speaker Models

This model NOT support multiple speakers. But You can check if Your model supports speakers and select a specific voice:

```python
from kani_tts import KaniTTS

model = KaniTTS('your_mode_repo/name')

# Check if model supports multiple speakers
print(f"Model type: {model.status}")  # 'singlspeaker' or 'multispeaker'

# Display available speakers (pretty formatted)
model.show_speakers()

# Or access the speaker list directly
print(model.speaker_list)

# Generate audio with a specific speaker
audio, text = model("Салам, менин атым Акылай. Бүгүн силерге кандай жардам бере алам?", speaker_id="speaker_n")
```

### Custom Configuration

```python
from kani_tts import KaniTTS

model = KaniTTS(
    'nineninesix/kani-tts-400m-ky-kani',
    temperature=0.7,           # 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")
```

### Playing Audio in Jupyter Notebooks

You can listen to generated audio directly in Jupyter notebooks or IPython:

```python
from kani_tts import KaniTTS
from IPython.display import Audio as aplay

model = KaniTTS('nineninesix/kani-tts-400m-ky-kani')
audio, text = model("Your text here")

# Play audio in notebook
aplay(audio, rate=model.sample_rate)
```

---



These tags help the model adjust tone, rhythm, and expressive style during speech synthesis.

## Use Cases
- **Conversational AI:** Real-time speech for chatbots and virtual assistants
- **Edge/Server Deployment:** Resource-efficient inference on affordable hardware
- **Accessibility:** Screen readers and language learning applications
- **Research:** Fine-tuning for specific voices, accents, or emotions
  
## Limitations
- Performance degrades with inputs exceeding 15 seconds (need to use sliding window chunking)
- Limited expressivity without fine-tuning for specific emotions
- May inherit biases from training data in prosody or pronunciation
- Optimized primarily for English; other languages may require additional training
  
## Optimization Tips
- **Multilingual Performance:** Continually pretrain on target language datasets and fine-tune NanoCodec
- **Batch Processing:** Use batches of 8-16 for high-throughput scenarios
- **Hardware:** Optimized for NVIDIA Blackwell architecture GPUs


## Resources

**Models:**
- **Pretrained Model:** [nineninesix/kani-tts-400m-0.3-pt](https://huggingface.co/nineninesix/kani-tts-400m-0.3-pt)
- **Space:** [nineninesix/KaniTTS-KyrGyz](https://huggingface.co/spaces/nineninesix/KaniTTS-KyrGyz)
  
**Examples:**
- **OpenAI compatible API Example**: https://github.com/nineninesix-ai/kanitts-vllm
- **Finetuning code pipeline:** https://github.com/nineninesix-ai/KaniTTS-Finetune-pipeline
- **Dataset preparation pipeline:** https://github.com/nineninesix-ai/nano-codec-dataset-pipeline
- **Example Dataset:** https://huggingface.co/datasets/nineninesix/expresso-conversational-en-nano-codec-dataset
- **GitHub Repository:** https://github.com/nineninesix-ai/kani-tts
- **ComfyUI node:** https://github.com/wildminder/ComfyUI-KaniTTS by [WildAi](https://github.com/wildminder)
- **NextJS basic app:** https://github.com/nineninesix-ai/open-audio. It uses the OpenAI npm package to connect to the OpenAI-compatible server API provided by [kanitts-vllm](https://github.com/nineninesix-ai/kanitts-vllm).
  
**Links:**
- **Website:** https://www.nineninesix.ai
- **Contact Form:** https://airtable.com/appX2G2TpoRk4M5Bf/pagO2xbIOjiwulPcP/form
  
## Acknowledgments
Built on top of [LiquidAI LFM2 350M](https://huggingface.co/LiquidAI/LFM2-350M) as the backbone and [Nvidia NanoCodec](https://huggingface.co/nvidia/nemo-nano-codec-22khz-0.6kbps-12.5fps) for audio processing.

## Responsible Use
**Prohibited activities include:**
- Illegal content or harmful, threatening, defamatory, or obscene material
- Hate speech, harassment, or incitement of violence
- Generating false or misleading information
- Impersonating individuals without consent
- Malicious activities such as spamming, phishing, or fraud
By using this model, you agree to comply with these restrictions and all applicable laws.

## Contact
Have a question, feedback, or need support? Please fill out our [contact form](https://airtable.com/appX2G2TpoRk4M5Bf/pagO2xbIOjiwulPcP/form) and we'll get back to you as soon as possible.

## Citation

```
@inproceedings{emilialarge,
  author={He, Haorui and Shang, Zengqiang and Wang, Chaoren and Li, Xuyuan and Gu, Yicheng and Hua, Hua and Liu, Liwei and Yang, Chen and Li, Jiaqi and Shi, Peiyang and Wang, Yuancheng and Chen, Kai and Zhang, Pengyuan and Wu, Zhizheng},
  title={Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation},
  booktitle={arXiv:2501.15907},
  year={2025}
}
```

```
@article{emonet_voice_2025,
  author={Schuhmann, Christoph and Kaczmarczyk, Robert and Rabby, Gollam and Friedrich, Felix and Kraus, Maurice and Nadi, Kourosh and Nguyen, Huu and Kersting, Kristian and Auer, Sören},
  title={EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection},
  journal={arXiv preprint arXiv:2506.09827},
  year={2025}
}
```