Voice AI has finally broken free from heavy hardware. NeuTTS Air is redefining text-to-speech as we know it, delivering studio-grade realism, instant voice cloning, and real-time generation directly on your device. Built by Neuphonic, the pioneers of fast, lightweight voice intelligence, NeuTTS Air is the world’s first on-device, super-realistic TTS model that doesn’t rely on internet access or proprietary APIs. Under the hood, it’s powered by a finely tuned 0.5B LLM backbone and the custom NeuCodec neural audio codec, striking the perfect balance between speed, quality, and efficiency. If you’re building a talking toy, a local voice assistant, or a compliance-safe enterprise app, NeuTTS Air’s architecture ensures buttery-smooth speech generation, instant response times, and low power consumption — even on laptops, phones, or Raspberry Pis. And with 3-second instant voice cloning, you can create custom voices that sound astonishingly human in both tone and emotion, all while keeping data securely on your device.
In this guide, we’ll show you exactly how to install and run NeuTTS Air locally, so you can experience the future of ultra-realistic, privacy-first, real-time speech generation in just a few minutes.
Prerequisites
The minimum system requirements for running this model are:
- GPU: 1x RTX4090
- Storage: 20 GB (preferable)
- VRAM: at least 16 GB
Step-by-step process to install and run NeuTTS Air
For the purpose of this tutorial, we’ll use a GPU-powered Virtual Machine by NodeShift since it provides high compute Virtual Machines at a very affordable cost on a scale that meets GDPR, SOC2, and ISO27001 requirements. Also, it offers an intuitive and user-friendly interface, making it easier for beginners to get started with Cloud deployments. However, feel free to use any cloud provider of your choice and follow the same steps for the rest of the tutorial.
Step 1: Setting up a NodeShift Account
Visit app.nodeshift.com and create an account by filling in basic details, or continue signing up with your Google/GitHub account.
If you already have an account, login straight to your dashboard.
Step 2: Create a GPU Node
After accessing your account, you should see a dashboard (see image), now:
- Navigate to the menu on the left side.
- Click on the GPU Nodes option.
- Click on Start to start creating your very first GPU node.
These GPU nodes are GPU-powered virtual machines by NodeShift. These nodes are highly customizable and let you control different environmental configurations for GPUs ranging from H100s to A100s, CPUs, RAM, and storage, according to your needs.
Step 3: Selecting configuration for GPU (model, region, storage)
- For this tutorial, we’ll be using 1x RTX4090 GPU, however, you can choose any GPU as per the prerequisites.
- Similarly, we’ll opt for 50 GB storage by sliding the bar. You can also select the region where you want your GPU to reside from the available ones.
Step 4: Choose GPU Configuration and Authentication method
- After selecting your required configuration options, you’ll see the available GPU nodes in your region and according to (or very close to) your configuration. In our case, we’ll choose a 1x RTX4090 24 GB GPU node with 64vCPUs/28GB RAM/50GB SSD.
2. Next, you’ll need to select an authentication method. Two methods are available: Password and SSH Key. We recommend using SSH keys, as they are a more secure option. To create one, head over to our official documentation.
Step 5: Choose an Image
The final step is to choose an image for the VM, which in our case is Nvidia Cuda.
That’s it! You are now ready to deploy the node. Finalize the configuration summary, and if it looks good, click Create to deploy the node.
Step 6: Connect to active Compute Node using SSH
- As soon as you create the node, it will be deployed in a few seconds or a minute. Once deployed, you will see a status Running in green, meaning that our Compute node is ready to use!
- Once your GPU shows this status, navigate to the three dots on the right, click on Connect with SSH, and copy the SSH details that appear.
As you copy the details, follow the below steps to connect to the running GPU VM via SSH:
- Open your terminal, paste the SSH command, and run it.
2. In some cases, your terminal may take your consent before connecting. Enter ‘yes’.
3. A prompt will request a password. Type the SSH password, and you should be connected.
Output:
Next, If you want to check the GPU details, run the following command in the terminal:
!nvidia-smi
Step 7: Set up the project environment with dependencies
- Create a virtual environment using Anaconda.
conda create -n tts python=3.11 -y && conda activate tts
Output:
2. Clone the official repository.
git clone https://github.com/neuphonic/neutts-air.git && cd neuttsair
Output:
3. Install required dependencies.
pip install -r requirements.txt
apt install espeak-ng
Output:
4. Create a new python file named app.py and paste the following Gradio app code inside it.
import os
import sys
sys.path.append("neutts-air")
from neuttsair.neutts import NeuTTSAir
import numpy as np
import gradio as gr
SAMPLES_PATH = os.path.join(os.getcwd(), "neutts-air", "samples")
DEFAULT_REF_TEXT = "So I'm live on radio. And I say, well, my dear friend James here clearly, and the whole room just froze. Turns out I'd completely misspoken and mentioned our other friend."
DEFAULT_REF_PATH = os.path.join(SAMPLES_PATH, "dave.wav")
DEFAULT_GEN_TEXT = "My name is Dave, and um, I'm from London."
tts = NeuTTSAir(
backbone_repo="neuphonic/neutts-air",
backbone_device="cuda",
codec_repo="neuphonic/neucodec",
codec_device="cuda"
)
def infer(
ref_text: str,
ref_audio_path: str,
gen_text: str,
) -> tuple[int, np.ndarray]:
"""
Generates speech using NeuTTS-Air given a reference audio and text, and new text to synthesize.
Args:
ref_text (str): The text corresponding to the reference audio.
ref_audio_path (str): The file path to the reference audio.
gen_text (str): The new text to synthesize.
Returns:
tuple [int, np.ndarray]: A tuple containing the sample rate (24000) and the generated audio waveform as a numpy array.
"""
gr.Info("Starting inference request!")
gr.Info("Encoding reference...")
ref_codes = tts.encode_reference(ref_audio_path)
gr.Info(f"Generating audio for input text: {gen_text}")
wav = tts.infer(gen_text, ref_codes, ref_text)
return (24_000, wav)
demo = gr.Interface(
fn=infer,
inputs=[
gr.Textbox(label="Reference Text", value=DEFAULT_REF_TEXT),
gr.Audio(type="filepath", label="Reference Audio", value=DEFAULT_REF_PATH),
gr.Textbox(label="Text to Generate", value=DEFAULT_GEN_TEXT),
],
outputs=gr.Audio(type="numpy", label="Generated Speech"),
title="NeuTTS-Air☁️",
description="Upload a reference audio sample, provide the reference text, and enter new text to synthesize."
)
if __name__ == "__main__":
demo.launch(allowed_paths=[SAMPLES_PATH], mcp_server=True, inbrowser=True)
Step 8: Launch the model with Gradio
1. Run the Gradio demo for inference.
python app.py
Output:
2. If you’re on a remote machine (e.g., NodeShift GPU), you’ll need to do SSH port forwarding in order to access the Gradio session on your local browser.
Run the following command in your local terminal after replacing:
<YOUR_SERVER_PORT> with the PORT allotted to your remote server (For the NodeShift server – you can find it in the deployed GPU details on the dashboard).
<PATH_TO_SSH_KEY> with the path to the location where your SSH key is stored.
<YOUR_SERVER_IP> with the IP address of your remote server.
ssh -L 7860:localhost:7860 -p <YOUR_SERVER_PORT> -i <PATH_TO_SSH_KEY> root@<YOUR_SERVER_IP>
After this copy the URL you received in your remote server: http://0.0.0.0:7860
And paste this on your local browser to access the Gradio session.
3. Once you upload a reference audio file with a text, the model will synthesize an audio of the refernece voice speaking the given text.
Here’s the original voice vs generated cloned voice outputs:
https://drive.google.com/drive/folders/1ZhyFIJw-AhKzXSaINJIRkUp2JDqx-iNz?usp=sharing
Conclusion
NeuTTS Air combines ultra-realistic speech, instant voice cloning, and efficient on-device performance to bring next-level TTS capabilities directly to your local machine. By following this guide, you can quickly install and run the model, exploring features like NeuCodec-powered audio, real-time inference, and custom speaker creation with just a few seconds of sample audio. NodeShift Cloud simplifies the setup and ensures smooth, GPU-accelerated deployment, giving you the infrastructure to experiment, prototype, or scale your voice AI projects effortlessly while keeping all data secure and local.
