OpenBMB’s VoxCPM introduces a completely new way of approaching Text-to-Speech by removing tokenization altogether and working directly in a continuous speech space. This design eliminates the rigid boundaries of traditional TTS systems and makes speech generation far more fluid and realistic. With its diffusion autoregressive architecture on top of the MiniCPM-4 backbone, VoxCPM captures not only the literal meaning of text but also its rhythm, tone, and emotional undertones. The result is speech that feels contextually aware, expressive, and strikingly natural, whether it’s narrating a story, reading dialogue, or responding conversationally. Even more impressive is its zero-shot voice cloning ability: from a short audio sample, VoxCPM can replicate a speaker’s voice with their timbre, accent, and subtle pacing intact, producing a result that is almost indistinguishable from the real person.
Beyond quality, VoxCPM is also designed for practicality. With an RTF as low as 0.17 on a standard RTX 4090 GPU, it supports near-instant speech generation, making it suitable for real-time use cases. In this article, we’ll dive into how can you deploy it locally and start using it in minutes.
Prerequisites
The minimum system requirements for running this model are:
- GPU: 1x RTX4090 or 1x RTX A6000 (depending on the use case scale)
- Storage: 10 GB (preferable)
- VRAM: at least 8 GB
- Anaconda installed
Step-by-step process to install and run VoxCPM
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 RTX A6000 GPU, however, you can choose any GPU as per the prerequisites.
- 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 GPU nodes in your region and according to (or very close to) your configuration. In our case, we’ll choose a 1x RTX A6000 48GB GPU node with 64vCPUs/63GB RAM/200GB 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.
We will switch to the Custom Image tab and select a specific Docker image that meets all runtime and compatibility requirements.
We choose the following image:
nvidia/cuda:12.1.1-devel-ubuntu22.04
This image is essential because it includes:
- Full CUDA toolkit (including
nvcc)
- Proper support for building and running GPU-based applications
- Compatibility with CUDA 12.1.1 required by certain model operations
Launch Mode
We selected:
Interactive shell server
This gives us SSH access and full control over terminal operations — perfect for installing dependencies, running benchmarks, and launching models.
Docker Repository Authentication
We left all fields empty here.
Since the Docker image is publicly available on Docker Hub, no login credentials are required.
Identification
nvidia/cuda:12.1.1-devel-ubuntu22.04
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 voxcpm python=3.11 -y && conda activate voxcpm
Output:
2. Clone the official repository and move nside the project directory.
git clone https://github.com/OpenBMB/VoxCPM.git && cd VoxCPM
Output:
3. Install required dependencies.
pip install -e .
apt update && apt install ffmpeg -y
Output:
4. Launch the Gradio demo. This will automatically download the model checkpoints as well.
python app.py
Output:
5. 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.
Step 8: Run the model
- Once you access the Gradio interface, it will look like this:
2. Generate speech from your given speaker’s audio (the one to be cloned) and prompt speech that is used in that audio along with the target prompt that you want to generate using the model.
Here’s the original speaker audio vs the generated AI audio of the same speaker:
https://drive.google.com/drive/folders/1_OedlyPELm3i0dziz_6cqT9h7IDmTuVc?usp=sharing
Conclusion
VoxCPM stands out as a next-generation TTS system by combining continuous-space speech modeling, context-aware expressiveness, and zero-shot voice cloning with impressive real-time performance. Its architecture not only advances speech synthesis quality but also makes lifelike and efficient deployment possible across diverse applications. With NodeShift Cloud, bringing these capabilities into practice becomes seamless, whether you want to experiment locally or scale up for production. By simplifying installation and deployment, NodeShift ensures that developers and creators can focus on leveraging VoxCPM’s strengths rather than wrestling with infrastructure, making cutting-edge speech synthesis truly accessible.
