Imagine an audio generation model so expressive, it can narrate a story with human-like cadence, speak in your cloned voice with melodic voice, or conduct a natural conversation between two completely different speakers, all in multiple languages and without any fine-tuning. That’s exactly what Higgs Audio v2 delivers. Pretrained on over 10 million hours of meticulously annotated audio and text, this powerful open-source audio foundation model pushes the boundaries of what’s possible in text-to-speech (TTS) and audio synthesis. Built on top of Llama 3.2-3B and enhanced with a novel DualFFN audio adapter architecture, Higgs Audio v2 combines the deep language understanding of LLMs with a cutting-edge discretized audio tokenizer capable of capturing both semantic and acoustic detail at just 25 fps. It excels in zero-shot prosody adaptation, multilingual translation, multi-speaker dialogue generation, and even simultaneous background music and speech synthesis. With state-of-the-art results on Seed-TTS Eval, ESD, and EmergentTTS-Eval, and win rates of up to 75.7% over GPT-4o-mini-TTS in emotion-rich generations, this model is not just a technical marvel, it’s an invitation to explore the future of voice AI.
If you’re ready to build with the next generation of audio intelligence, this guide will walk you through installing Higgs Audio v2 locally, unlocking everything from high-fidelity narration to real-time multilingual voice cloning, right on your machine.
Prerequisites
The minimum system requirements for running this model are:
- GPU: 1x RTX4090 or 1x RTX A6000
- Storage: 50 GB (preferable)
- VRAM: at least 16 GB
- Anaconda installed
Step-by-step process to install and run Higgs Audio v2
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.
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 higgs python=3.11 -y && conda activate higgs
Output:
2. Once you’re inside the environment, clone the official repository.
git clone https://github.com/boson-ai/higgs-audio.git
cd higgs-audio
Output:
3. Install required dependencies.
pip install -r requirements.txt
pip install -e .
4. Install PyTorch, transformers and other python packages.
pip install torch torchvision torchaudio
pip install einops timm pillow
pip install transformers==4.47.0 git+https://github.com/huggingface/accelerate
pip install git+https://github.com/huggingface/diffusers
pip install huggingface_hub
pip install sentencepiece bitsandbytes protobuf decord numpy ffmpeg
5. Install and run jupyter notebook.
conda install -c conda-forge --override-channels notebook -y
conda install -c conda-forge --override-channels ipywidgets -y
jupyter notebook --allow-root
6. If you’re on a remote machine (e.g., NodeShift GPU), you’ll need to do SSH port forwarding in order to access the jupyter notebook 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 8888:localhost:8888 -p <YOUR_SERVER_PORT> -i <PATH_TO_SSH_KEY> root@<YOUR_SERVER_IP>
Output:
After this copy the URL you received in your remote server:
And paste this on your local browser to access the Jupyter Notebook session.
Step 8: Download and Run the model
- Open a Python notebook inside Jupyter.
2. Download the model checkpoints.
from boson_multimodal.serve.serve_engine import HiggsAudioServeEngine, HiggsAudioResponse
from boson_multimodal.data_types import ChatMLSample, Message, AudioContent
import torch
import torchaudio
import time
import click
MODEL_PATH = "bosonai/higgs-audio-v2-generation-3B-base"
AUDIO_TOKENIZER_PATH = "bosonai/higgs-audio-v2-tokenizer"
system_prompt = (
"Generate audio following instruction.\n\n<|scene_desc_start|>\nAudio is recorded from a quiet room.\n<|scene_desc_end|>"
)
messages = [
Message(
role="system",
content=system_prompt,
),
Message(
role="user",
content="The sun rises in the east and sets in the west. This simple fact has been observed by humans for thousands of years.",
),
]
device = "cuda" if torch.cuda.is_available() else "cpu"
serve_engine = HiggsAudioServeEngine(MODEL_PATH, AUDIO_TOKENIZER_PATH, device=device)
output: HiggsAudioResponse = serve_engine.generate(
chat_ml_sample=ChatMLSample(messages=messages),
max_new_tokens=1024,
temperature=0.3,
top_p=0.95,
top_k=50,
stop_strings=["<|end_of_text|>", "<|eot_id|>"],
)
torchaudio.save(f"output.wav", torch.from_numpy(output.audio)[None, :], output.sampling_rate)
Output:
Conclusion
Higgs Audio v2 showcases the cutting edge of expressive audio generation, from zero-shot multilingual TTS to realistic multi-speaker dialogues, all powered by innovations like DualFFN architecture, a unified audio tokenizer, and training on 10 million hours of diverse audio. Installing it locally opens the door to these advanced capabilities for developers, researchers, and creatives alike. Powered by NodeShift Cloud, the deployment process becomes even more seamless, offering scalable compute, fast storage, and integrated tooling that accelerates experimentation and production workflows.
