neutts-nano

[](https://www.youtube.com/watch?v=_USVA-JA0o0) [🚀 Spaces Demo](https://huggingface.co/spaces/neuphonic/neutts-nano-multilingual-collection), [🔧 Github](https://github.com/neuphonic/neutts) [Q8 GGUF version](https://huggingface.co/neuphonic/neutts-nano-q8-gguf), [Q4 GGUF version](https://huggingface.co/neuphonic/neutts-nano-q4-gguf) *Created by [Neuphonic](http://neuphonic.com/) - building faster, smaller, on-device voice AI* State-of-the-art Voice AI has been locked behind web APIs for too long. The **NeuTTS Nano Multilingual Collection** is a collection of super-fast, highly realistic, **on-device** TTS speech language models with **instant voice cloning** - built to run smoothly on CPUs and edge devices. With a compact backbone and an efficient LM + codec design, Nano models deliver strong naturalness and cloning quality at a fraction of the compute, making them ideal for embedded voice agents, assistants, toys, and privacy-sensitive applications. > [!NOTE] > This model is **English only**: see the [multilingual collection page](https://huggingface.co/collections/neuphonic/neutts-nano-multilingual-collection) for other languages. - ⚡️ **Ultra-fast for on-device** — built for real-time or better-than-real-time generation on laptop-class CPUs - 🗣 **High realism for its size** — natural, expressive speech in a comp act footprint - 👫 **Instant voice cloning** — create a new speaker from just a few seconds of audio - 📦 **GGUF/GGML-friendly deployment** — easy to run locally via CPU-first tooling - 🔒 **Local-first + compliance-friendly** — keep audio and text on-device > [!CAUTION] > Websites like neutts.com are popping up and they're not affliated with Neuphonic, our github or this repo. > > We are on neuphonic.com only. Please be careful out there! 🙏 NeuTTS Nano models are designed for **maximum speed per parameter** while retaining strong speaker similarity and naturalness: - **Backbone**: compact LM backbone tuned for TTS token generation (Nano class) - **Audio Codec**: [NeuCodec](https://huggingface.co/neuphonic/neucodec) - our open-source neural audio codec that achieves exceptional audio quality at low bitrates using a single codebook - **Format**: quantisations available in GGUF format for efficient on-device inference - **Responsibility**: Watermarked outputs - **Inference Speed**: Optimised for real-time generation on CPUs - **Power Consumption**: Designed for mobile and embedded devices - **Active params (backbone only):** **~116.8M** - **Total params (backbone + tied embeddings/head):** **~228.7M** 1. **Install System Dependencies (required): `espeak-ng`** > [!CAUTION] > `espeak-ng` is an updated version of `espeak`, as of February 2026 on version 1.52.0. Older versions of `espeak` and `espeak-ng` can exhibit significant phonemisation issues, particularly for non-English languages. Updating your system version of `espeak-ng` to the latest version possible is highly recommended. > [!NOTE] > `brew` on macOS Ventura and later, `apt` in Ubuntu version 25 or Debian version 13, and `choco`/`winget` on Windows, install the latest version of `espeak-ng` with the commands below. If you have a different or older operating system, you may need to install from source: see the following link https://github.com/espeak-ng/espeak-ng/blob/master/docs/building.md Please refer to the following link for instructions on how to install `espeak-ng`: https://github.com/espeak-ng/espeak-ng/blob/master/docs/guide.md brew install espeak-ng sudo apt install espeak-ng choco install espeak-ng winget install -e --id eSpeak-NG.eSpeak-NG Windows users who installed via msi / do not have their install on path need to run the following (see https://github.com/bootphon/phonemizer/issues/163) $env:PHONEMIZER_ESPEAK_LIBRARY = "c:\Program Files\eSpeak NG\libespeak-ng.dll" $env:PHONEMIZER_ESPEAK_PATH = "c:\Program Files\eSpeak NG" setx PHONEMIZER_ESPEAK_LIBRARY "c:\Program Files\eSpeak NG\libespeak-ng.dll" setx PHONEMIZER_ESPEAK_PATH "c:\Program Files\eSpeak NG" 2. **Install NeuTTS** pip install neutts Or for a local editable install, clone the [neutts repository](https://github.com/neuphonic/neutts) and run in the base folder: pip install -e . Alternatively to install all dependencies, including `onnxruntime` and `llama-cpp-python` (equivalent to steps 3 and 4 below): pip install neutts[all] or for an editable install: pip install -e .[all] 3. **(Optional) Install `llama-cpp-python` to use `.gguf` models.** pip install "neutts[llama]" Note that this installs `llama-cpp-python` without GPU support. To install with GPU support (e.g., CUDA, MPS) please refer to: https://pypi.org/project/llama-cpp-python/ 4. **(Optional) Install `onnxruntime` to use the `.onnx` decoder.** pip install "neutts[onnx]" To get started with the example scripts, clone the neutts repository and navigate into the project directory: git clone https://github.com/neuphonic/neutts.git cd neutts Several examples are available, including a Jupyter notebook in the `examples` folder. Run the basic example script to synthesize speech: python -m examples.basic_example \ --input_text "My name is Andy. I'm 25 and I just moved to London. The underground is pretty confusing, but it gets me around in no time at all." \ --ref_audio samples/jo.wav \ --ref_text samples/jo.txt To specify a particular model repo for the backbone or codec, add the --backbone argument. Available backbones are listed in the [NeuTTS Nano Multilingual Collection](https://huggingface.co/collections/neuphonic/neutts-nano-multilingual-collection) huggingface collection. > [!CAUTION] > It is highly recommended to use a same-language reference for best performance: see [this readme section](https://github.com/neuphonic/neutts/tree/main?tab=readme-ov-file#example-reference-files) for appropriate example references. from neutts import NeuTTS import soundfile as sf tts = NeuTTS( backbone_repo="neuphonic/neutts-nano", backbone_device="cpu", codec_repo="neuphonic/neucodec", codec_device="cpu", ) input_text = "My name is Andy. I'm 25 and I just moved to London. The underground is pretty confusing, but it gets me around in no time at all." ref_text_path = "samples/jo.txt" ref_audio_path = "samples/jo.wav" ref_text = open(ref_text_path, "r").read().strip() ref_codes = tts.encode_reference(ref_audio_path) wav = tts.infer(input_text, ref_codes, ref_text) sf.write("test.wav", wav, 24000) NeuTTS Nano requires two inputs: 1. A reference audio sample (`.wav` file) 2. A text string The model then synthesises the text as speech in the style of the reference audio. This is what enables NeuTTS Nano’s instant voice cloning capability. You can find some ready-to-use samples in the `samples` folder: - `samples/dave.wav` - `samples/jo.wav` For optimal performance, reference audio samples should be: - **Mono channel** - **16-44 kHz** sample rate - **3–15 seconds** in length - Saved as a **`.wav`** file - **Clean** — minimal to no background noise - **Natural, continuous speech** — like a monologue or conversation, with few pauses, so the model can capture tone effectively