HuggingFace 🤗: Model, Q8 GGUF, Q4 GGUF Spaces

Created by Neuphonic - 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.

• 🗣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

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:

• Supported Languages: English
• Audio Codec: NeuCodec - our 50hz neural audio codec that achieves exceptional audio quality at low bitrates using a single codebook
• Context Window: 2048 tokens, enough for processing ~30 seconds of audio (including prompt duration)
• 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

1. Clone Git Repo

   git clone https://github.com/neuphonic/neutts-air.git

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

   # Mac OS
   brew install espeak
   
   # Ubuntu/Debian
   sudo apt install espeak

   Mac users may need to put the following lines at the top of the neutts.py file.

   from phonemizer.backend.espeak.wrapper import EspeakWrapper
   _ESPEAK_LIBRARY = '/opt/homebrew/Cellar/espeak/1.48.04_1/lib/libespeak.1.1.48.dylib'  #use the Path to the library.
   EspeakWrapper.set_library(_ESPEAK_LIBRARY)

   Windows users may need to run (see bootphon/phonemizer#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"

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
   

4. (Optional) Install Llama-cpp-python to use the GGUF models.

   pip install llama-cpp-python
   

   To run llama-cpp with GPU suport (CUDA, MPS) support please refer to: https://pypi.org/project/llama-cpp-python/

5. (Optional) Install onnxruntime to use the .onnx decoder. If you want to run the onnxdecoder

Run the basic example script to synthesize speech:

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.

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

from neuttsair.neutts import NeuTTSAir
import soundfile as sf

tts = NeuTTSAir(
   backbone_repo="neuphonic/neutts-air", # or 'neutts-air-q4-gguf' with llama-cpp-python installed
   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)

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.

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

• samples/dave.wav
• samples/jo.wav

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

For optimal performance on-device:

1. Use the GGUF model backbones
2. Pre-encode references
3. Use the onnx codec decoder

Take a look at this example examples README to get started.

Every audio file generated by NeuTTS Air includes Perth (Perceptual Threshold) Watermarker.

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

To run the pre commit hooks to contribute to this project run:

Then: