When it comes to bringing human emotion into synthetic voices, Maya1 by Maya Research stands out as one of the most expressive open-source speech models ever released. Built for precise voice design and emotional realism, Maya1 allows you to generate lifelike speech that can laugh, cry, whisper, sigh, gasp, and express over 20 nuanced emotions, all through simple natural language prompts. With a powerful 3B-parameter architecture and the cutting-edge SNAC neural codec for real-time streaming, it bridges the gap between emotionless TTS models and true expressive voice synthesis. Whether you’re a developer crafting immersive games, a content creator seeking authentic narration, or an AI researcher exploring emotional speech, Maya1 gives you the power to create dynamic, humanlike voices that respond intuitively to your instructions.
Even more impressive, Maya1 is lightweight enough to run on a single GPU, open-sourced under the Apache 2.0 license, and ready to experiment with directly in its interactive Playground. In this guide, we’ll walk you through how to install and run Maya1 locally, so you can experience expressive, emotionally rich voice generation right from your own machine.
Prerequisites
The minimum system requirements for running this model are:
- GPU: 1x RTX4090 or 1x RTX A6000 (depending on the use case scale)
- Storage: 20 GB (preferable)
- VRAM: at least 8 GB
- Anaconda installed
Step-by-step process to install and run Maya1
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 with Anaconda.
conda create -n maya python=3.11 -y && conda activate maya
Output:
2. Install required packages and dependencies.
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
pip install git+https://github.com/huggingface/transformers
pip install git+https://github.com/huggingface/accelerate
pip install git+https://github.com/huggingface/diffusers
pip install huggingface_hub
pip install einops timm pillow
pip install sentencepiece bitsandbytes protobuf decord numpy
Output:
3. 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
4. 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
- Download model checkpoints and run model for inference.
from transformers import AutoModelForCausalLM, AutoTokenizer
from snac import SNAC
import soundfile as sf
# Load the best open source voice AI model
model = AutoModelForCausalLM.from_pretrained(
"maya-research/maya1",
dtype=torch.bfloat16,
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("maya-research/maya1")
llm_device = next(model.parameters()).device
# Load SNAC audio decoder (24kHz)
snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz").eval().to("cuda")
snac_device = next(snac_model.parameters()).device
# Design your voice with natural language
description = "Robotic male voice with unnatural intonation, beeps, boops, and fast pacing"
text = "Hello! This is Maya1 <laugh> the best open source voice AI model with emotions."
# Create chat-formatted prompt so the model emits SNAC audio tokens
messages = [
{"role": "system", "content": "You are Maya, a voice AI that responds with SNAC audio tokens."},
{"role": "user", "content": f'<description="{description}"> {text}'},
]
chat = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt",
).to(llm_device)
input_ids = chat["input_ids"]
attention_mask = chat["attention_mask"] if "attention_mask" in chat else torch.ones_like(input_ids)
# Generate emotional speech
with torch.inference_mode():
outputs = model.generate(
input_ids=input_ids,
attention_mask=attention_mask,
max_new_tokens=500,
temperature=0.4,
top_p=0.9,
do_sample=True,
)
# Extract SNAC audio tokens
generated_ids = outputs[0, input_ids.shape[1]:]
snac_tokens = [t.item() for t in generated_ids if 128266 <= t <= 156937]
if not snac_tokens:
raise RuntimeError("Model did not emit any SNAC audio tokens. Try adjusting the prompt or sampling settings.")
# Decode SNAC tokens to audio frames
frames = len(snac_tokens) // 7
snac_tokens = snac_tokens[: frames * 7] # drop incomplete frames, if any
codes = [[], [], []]
for i in range(frames):
s = snac_tokens[i * 7 : (i + 1) * 7]
codes[0].append((s[0] - 128266) % 4096)
codes[1].extend([(s[1] - 128266) % 4096, (s[4] - 128266) % 4096])
codes[2].extend(
[
(s[2] - 128266) % 4096,
(s[3] - 128266) % 4096,
(s[5] - 128266) % 4096,
(s[6] - 128266) % 4096,
]
)
# Generate final audio with SNAC decoder
codes_tensor = [torch.tensor(c, dtype=torch.long, device=snac_device).unsqueeze(0) for c in codes]
with torch.inference_mode():
audio = snac_model.decoder(snac_model.quantizer.from_codes(codes_tensor))[0, 0].cpu().numpy()
# Save your emotional voice output
sf.write("output.wav", audio, 24000)
print("Voice generated successfully! Play output.wav")```
I was able to get it to run past the SNAC errors, by improving chat format template following - but it produces random voices and words
Output:
Here’s the generated audio: https://drive.google.com/drive/folders/1vHT-FXwRegLkTen9FjdnV_-axrxncEae?usp=sharing
Conclusion
Maya1 by Maya Research redefines expressive voice synthesis by combining fine-grained emotional control, natural language voice design, and real-time streaming into a single, accessible model. Through this guide, we explored how to install and run Maya1 locally to unlock its full creative potential for developers, storytellers, and AI enthusiasts alike. Powered by NodeShift Cloud’s seamless infrastructure, deploying Maya1 becomes faster and more reliable, enabling users to experiment with high-quality speech generation, test models effortlessly, and scale their projects without complex setup. Together, Maya1’s emotional depth and NodeShift Cloud’s robust environment make it easier than ever to create truly humanlike voice experiences.
