---
license: apache-2.0
pipeline_tag: text-to-speech
tags:
- audio
- speech
- speech-language-models
datasets:
- amphion/Emilia-Dataset
- neuphonic/emilia-yodas-english-neucodec
---

# NeuTTS Air ☁️ 

[![NeuTTSAir_Intro](neutts-air.png)](https://www.youtube.com/watch?v=YAB3hCtu5wE)

[🚀 Spaces Demo](https://huggingface.co/spaces/neuphonic/neutts-air), [🔧 Github](https://github.com/neuphonic/neutts-air)

[Q8 GGUF version](https://huggingface.co/neuphonic/neutts-air-q8-gguf), [Q4 GGUF version](https://huggingface.co/neuphonic/neutts-air-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. NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps.

## Key Features

- 🗣Best-in-class realism for its size - produces natural, ultra-realistic voices that sound human
- 📱Optimised for on-device deployment - provided in GGML format, ready to run on phones, laptops, or even Raspberry Pis
- 👫Instant voice cloning - create your own speaker with as little as 3 seconds of audio
- 🚄Simple LM + codec architecture built off a 0.5B backbone - the sweet spot between speed, size, and quality for real-world applications


> [!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! 🙏


## Model Details

NeuTTS Air is built off Qwen 0.5B - a lightweight yet capable language model optimised for text understanding and generation - as well as a powerful combination of technologies designed for efficiency and quality:

- **Audio Codec**: [NeuCodec](https://huggingface.co/neuphonic/neucodec) - our proprietary neural audio codec that achieves exceptional audio quality at low bitrates using a single codebook
- **Format**: Available in GGML format for efficient on-device inference
- **Responsibility**: Watermarked outputs
- **Inference Speed**: Real-time generation on mid-range devices
- **Power Consumption**: Optimised for mobile and embedded devices

## Get Started

1. **Clone the [Git Repo](https://github.com/neuphonic/neutts-air)**
    
    ```bash
    git clone https://github.com/neuphonic/neutts-air.git
    cd neuttsair
    ```
    
2. **Install `espeak` (required dependency)**
    
    Please refer to the following link for instructions on how to install `espeak`:
    
    https://github.com/espeak-ng/espeak-ng/blob/master/docs/guide.md
    
    ```bash
    # Mac OS
    brew install espeak
    
    # Ubuntu/Debian
    sudo apt install espeak

    # Arch Linux
    paru -S aur/espeak
    ```
    
3. **Install Python dependencies**
    
    The requirements file includes the dependencies needed to run the model with PyTorch. When using an ONNX decoder or a GGML model, some dependencies (such as PyTorch) are no longer required.
    
    The inference is compatible and tested on `python>=3.11`.
    
    ```
    pip install -r requirements.txt
    
    ```
    

## **Basic Example**

Run the basic example script to synthesize speech:

```bash
python -m examples.basic_example \
  --input_text "My name is Dave, and um, I'm from London" \
  --ref_audio samples/dave.wav \
  --ref_text samples/dave.txt

```

To specify a particular model repo for the backbone or codec, add the `--backbone` argument. Available backbones are listed in [NeuTTS-Air huggingface collection](https://huggingface.co/collections/neuphonic/neutts-air-68cc14b7033b4c56197ef350).

Several examples are available, including a Jupyter notebook in the `examples` folder.

### **Simple One-Code Block Usage**

```python
from neuttsair.neutts import NeuTTSAir
import soundfile as sf

tts = NeuTTSAir( backbone_repo="neuphonic/neutts-air-q4-gguf", backbone_device="cpu", codec_repo="neuphonic/neucodec", codec_device="cpu")
input_text = "My name is Dave, and um, I'm from London."

ref_text = "samples/dave.txt"
ref_audio_path = "samples/dave.wav"

ref_text = open(ref_text, "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)

```

# Tips

NeuTTS Air 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 Air’s instant voice cloning capability.

### Example Reference Files

You can find some ready-to-use samples in the `examples` folder:

- `samples/dave.wav`
- `samples/jo.wav`

### Guidelines for Best Results

For optimal performance, reference audio samples should be:

1. **Mono channel**
2. **16-44 kHz sample rate**
3. **3–15 seconds in length**
4. **Saved as a `.wav` file**
5. **Clean** — minimal to no background noise
6. **Natural, continuous speech** — like a monologue or conversation, with few pauses, so the model can capture tone effectively

# **Responsibility**

Every audio file generated by NeuTTS Air includes [**Perth (Perceptual Threshold) Watermarker](https://github.com/resemble-ai/perth).**

# **Disclaimer**

Don't use this model to do bad things… please.