Zonos-v0.1 is an advanced open-weight text-to-speech (TTS) model designed to deliver hyper-realistic and expressive speech generation. It has been trained on over 200,000 hours of diverse, multilingual speech, which makes it capable enough to compete with or even surpass the top commercial TTS solutions in terms of quality and naturalness. Whether you’re looking to generate natural speech from text prompts, perform high-fidelity voice cloning with just a few minutes or hours of reference audio, or fine-tune speech characteristics like pitch, speaking rate, and emotional tone, Zonos-v0.1 is becoming the next go-to speech generation tool for all of these tasks. With easy local setup and accessibility via its intuitive Gradio interface, it’s an ideal choice for developers, content creators, and AI researchers looking to push the boundaries of synthetic speech.
In this guide, we’ll see how to install Zonos locally or on a GPU and access the interface by launching it on Gradio.
Prerequisites
The minimum system requirements for this use case are:
- GPUs: Preferably RTX 3000-series or newer
- Disk Space: 200 GB
- RAM: At least 8 GB.
- Nvidia Cuda installed.
Note: The prerequisites for this are highly variable across use cases. A high-end configuration could be used for a large-scale deployment.
Step-by-step process to install & run Zonos-v0.1
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 the RTX 4090 GPU; however, you can choose any GPU of your choice based on your needs.
- Similarly, we’ll opt for 200GB 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 VMs in your region and according to (or very close to) your configuration. In our case, we’ll choose a 1x RTX 4090 GPU node with 12 vCPUs/96GB RAM/200 GB 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 would be to choose an image for the VM, which in our case is Nvidia Cuda, where we’ll deploy and run the inference of our model.
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 and click on Connect with SSH. This will open a new tab with a Jupyter Notebook session in which we can run our model.
Step 7: Install Zonos with dependencies
- Update and upgrade Ubuntu packages for latest versions and patches.
apt update && apt upgrade -y
2. Install dependency.
apt install -y espeak-ng
Output:
3. Clone the Zonos official repository.
git clone https://github.com/Zyphra/Zonos
Output:
4. Move inside the project directory and create a virtual environment specifying the Python version.
Make sure you have Anaconda installed in your system to create a virtual environment with conda.
(replace <ENVIRONEMENT_NAME> with a name for the virtual environment, e.g. zonos-env)
cd Zonos
conda create -n <ENVIRONMENT_NAME> python=3.10
Output:
5. Activate the environment and install python dependencies.
conda activate <ENVIRONEMENT_NAME>
pip install -e .
6. Compile the packages.
pip install --no-build-isolation -e .[compile]
Output:
Step 8: Access the Zonos Gradio interface
Once all the above installations are done, we can move forward to access the Gradio interface where we can test the model.
- Make sure you are inside the project directory in the virtual environment and run this command:
python3 gradio_interface.py
Output:
The above command will open an interface on http://0.0.0.0:7860
2. Forward the port to access the URL from outside the remote server.
If you are running the model in a remote server (for e.g. NodeShift GPU), then you will need to do SSH port forwarding for making it accessible in your local web 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>
Output:
Once you are connected, you can access the Zonos interface at http://localhost:7860 in your local machine. The web interface looks like this:
In the above interface, you can upload your own speaker audio inputs for the model to clone the speaker’s voice. Also, you can play with different parameters to customize the speaker’s voice as per your requirements.
Conclusion
Installing Zonos-v0.1 locally enables high-quality speech generation, voice cloning, and fine-tuned audio control without relying on external services. By following this guide, you’ve set up the model on your machine or GPU, allowing simplified access through Gradio’s intuitive interface. For those seeking a scalable and efficient deployment, the NodeShift cloud platform offers a powerful all-in-one place, ensuring optimized performance, easy resource management, and hassle-free access to the model from anywhere, all without breaking the bank!
