When it comes to next-generation text-to-speech technology, IndexTTS2 is a breakthrough you don’t want to miss. Unlike traditional autoregressive TTS models that struggle with precise duration control, IndexTTS2 introduces an innovative mechanism that lets you decide exactly how long your generated speech should last, making it a game-changer for applications like video dubbing, lip-syncing, and immersive storytelling. The model offers two flexible modes: one where you explicitly control the number of tokens for precise duration alignment, and another where speech is generated naturally without constraints while preserving rhythm, intonation, and prosody. But IndexTTS2 goes far beyond timing control, it disentangles emotional tone from speaker identity, giving you the power to mix and match timbre and emotions independently. Want your favorite voice speaking with heartfelt excitement or calm authority? IndexTTS2 makes it possible. It also incorporates GPT latent representations and a three-stage training paradigm, ensuring crystal-clear, stable speech even during highly emotional expressions. To make emotional customization easier, the team even designed a soft instruction mechanism that lets you guide voice generation with simple text prompts, no technical expertise required. Backed by state-of-the-art benchmarks in speaker similarity, word error rate, and emotional fidelity, this model sets a new standard for expressive, controllable, and lifelike TTS.
In this article we are going to walk you through the simple straightforward steps to get this model up and running in you local machine or GPU-acclerated environment in minutes.
Prerequisites
The minimum system requirements for running this model are:
- GPU: 1x RTX4090 or 1x RTX A6000
- Storage: 20 GB (preferable)
- VRAM: at least 12 GB
Step-by-step process to install and run IndexTTS2
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/84GB RAM/100GB SSD with CUDA 12.9 as the maximum supported version.
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.
In our previous blogs, we used pre-built images from the Templates tab when creating a Virtual Machine. However, for running IndexTTS, we need CUDA version of atleast 12.8 or greater as mentioned in their requirements. That’s why, in this case, we switched to the Custom Image tab and selected a specific Docker image that meets all runtime and compatibility requirements.
We chose the following image:
nvidia/cuda:12.9.0-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 12.9.0 required by 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:12.9.0-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
- Update the Ubuntu system package source list and install required packages.
apt update && apt install -y git python3-pip
2. Install uv package manager.
curl -LsSf https://astral.sh/uv/install.sh | sh
Output:
3. Clone the official repository.
git clone https://github.com/index-tts/index-tts.git && cd index-tts
Output:
4. Login to Hugging Face with HF READ token.
This is a gated model, make sure to get access granted from the model card.
hf auth login
Output:
5. Install all project dependencies.
pip install huggingface_hub
uv sync --all-extras
Output:
Step 8: Download and Run the model
- Download the model files.
huggingface-cli download --resume-download IndexTeam/IndexTTS-2 --local-dir checkpoints --local-dir-use-symlinks False
Output:
2. Run the Gradio demo for inference.
uv run webui.py
Output:
3. 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.
4. 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/1GUojYD1SklaIKE6XSE3L1xOHNXeoDfC4?usp=sharing
Conclusion
IndexTTS2 brings together precision, flexibility, and emotional depth in a way no other TTS model has achieved, offering both strict duration control and natural prosody, along with independent tuning of timbre and emotion for truly lifelike voice synthesis. By following the steps outlined in this guide, you can quickly set up and run the model locally, unlocking its full potential for projects like dubbing, narration, or creative audio generation. With NodeShift making the installation process seamless and GPU-accelerated deployment effortless, you not only gain access to cutting-edge speech technology but also the infrastructure to scale it smoothly for research, prototyping, or production.
