--- license: other license_name: lfm1.0 license_link: https://www.liquid.ai/lfm-license language: - en - ja - de - ar - zh - es - ko - ky pipeline_tag: text-to-speech library_name: transformers datasets: - laion/Emolia - NightPrince/MasriSpeech-Full ---

Logo

# KaniTTS Pretrain v0.3 [![](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:** English, Chinese, Korean, Spanish, German, Japanese, German, Kyrgyz - **License:** Apache 2.0 ## 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-0.3-pt') # Generate audio from text audio, text = model("Your text here") # 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("Your text here", speaker_id="speaker_n") ``` ### Custom Configuration ```python from kani_tts import KaniTTS model = KaniTTS( 'nineninesix/kani-tts-400m-0.3-pt', 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-0.3-pt') audio, text = model("Your text here") # Play audio in notebook aplay(audio, rate=model.sample_rate) ``` --- ## 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 | ## Datasets - https://huggingface.co/datasets/laion/Emolia - https://huggingface.co/datasets/nytopop/expresso-conversational - https://huggingface.co/datasets/NightPrince/MasriSpeech-Full ## 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:** https://huggingface.co/nineninesix/kani-tts-500m-0.3-pt - **English:** https://huggingface.co/nineninesix/kani-tts-400m-en - **Chinese:** https://huggingface.co/nineninesix/kani-tts-400m-zh - **Korean:** https://huggingface.co/nineninesix/kani-tts-400m-ko - **German:** https://huggingface.co/nineninesix/kani-tts-400m-de - **Spanish:** https://huggingface.co/nineninesix/kani-tts-400m-es - **Arabic:** https://huggingface.co/nineninesix/kani-tts-400m-ar - **Japanese:** https://huggingface.co/nineninesix/kani-tts-370m-expo2025-osaka-ja **Examples:** - **Space:** https://huggingface.co/spaces/nineninesix/KaniTTS - **OpenAI compatible API**: 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 - **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). - **GitHub Repository:** https://github.com/nineninesix-ai/kani-tts **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} } ``` ``` @dataset{masrispeech_full, author = {Yahya Muhammad Alnwsany}, title = {MasriSpeech-Full: Large-Scale Egyptian Arabic Speech Corpus}, year = {2025}, publisher = {Hugging Face}, url = {https://huggingface.co/collections/NightPrince/masrispeech-dataset-68594e59e46fd12c723f1544} } ```