ZONOS2-BF16

This repository provides a BF16 Safetensors conversion of the original Zyphra/ZONOS2 model for use with the ZONOS2 TTS ComfyUI custom node.

The model was converted from the original PyTorch checkpoint format to .safetensors for easier loading, safer serialization, and direct integration with ComfyUI workflows.

Original Project

ZONOS2 is a text-to-speech model from Zyphra trained on more than 6 million hours of varied multilingual speech. It supports expressive speech generation and high-fidelity voice cloning.

ComfyUI Custom Node

This model package is intended for use with:

• https://github.com/Saganaki22/Zonos2_TTS-ComfyUI

The ComfyUI node provides native ZONOS2 text-to-speech, audio-only voice cloning, BF16/FP16 loading, SDPA/FlashAttention inference, progress reporting, and ComfyUI/AIMDO model-management integration.

Model File

Main model file:

• zonos2-bf16.safetensors

Direct download:

• https://huggingface.co/drbaph/ZONOS2-BF16/resolve/main/zonos2-bf16.safetensors?download=true

Model Storage Location

Place the model and required assets under:

ComfyUI/
└── models/
    └── zonos2/
        ├── zonos2-bf16.safetensors
        ├── dac_44khz/
        └── speaker_encoder/

Expected layout:

ComfyUI/models/zonos2/
├── zonos2-bf16.safetensors
├── dac_44khz/
│   ├── config.json
│   ├── dac_model.bin
│   └── preprocessor_config.json
└── speaker_encoder/
    ├── config.json
    ├── model.safetensors
    └── preprocessor_config.json

If download_if_missing is enabled in the ComfyUI node, missing assets can be downloaded automatically.

Usage

Install the ComfyUI custom node:

cd ComfyUI/custom_nodes
git clone https://github.com/Saganaki22/Zonos2_TTS-ComfyUI.git

Then restart ComfyUI and load the ZONOS2 model from the node loader.

Notes

• This repository is a converted BF16 Safetensors package of the original ZONOS2 model.
• The model architecture and original weights come from Zyphra/ZONOS2.
• This package is provided for ComfyUI compatibility and convenience.
• Voice cloning should only be used with voices you own or have explicit permission to use.

License

The original ZONOS2 model is released under the Apache License 2.0.

This converted Safetensors package follows the same model license.

Citation

If you find this model useful in an academic context, please cite the original ZONOS2 work:

@misc{zyphra2025zonos,
  title     = {Zonos V2 Technical Report},
  author    = {Gabriel Clark, Sofian Mejjoute, Mohamed Osman, George Close, Beren Millidge},
  year      = {2026},
}

Credits

• Original model: https://github.com/Zyphra/ZONOS2
• Original Hugging Face repository: https://huggingface.co/Zyphra/ZONOS2
• BF16 Safetensors package: https://huggingface.co/drbaph/ZONOS2-BF16
• ComfyUI custom node: https://github.com/Saganaki22/Zonos2_TTS-ComfyUI