--- license: apache-2.0 pipeline_tag: text-to-speech library_name: ZONOS2 tags: - zonos2 - text-to-speech - voice-clone - clone - voice - tts - comfyui - bf16 --- # ZONOS2-BF16 This repository provides a **BF16 Safetensors conversion** of the original [Zyphra/ZONOS2](https://huggingface.co/Zyphra/ZONOS2) model for use with the [ZONOS2 TTS ComfyUI custom node](https://github.com/Saganaki22/Zonos2_TTS-ComfyUI). The model was converted from the original PyTorch checkpoint format to `.safetensors` for easier loading, safer serialization, and direct integration with ComfyUI workflows. ![Screenshot 2026-06-12 214924](https://cdn-uploads.huggingface.co/production/uploads/63473b59e5c0717e6737b872/aWr3cHXPHERGSyYG2hvMT.png) ## 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. ![zonos2](https://cdn-uploads.huggingface.co/production/uploads/63473b59e5c0717e6737b872/Aiw3SXr27w4SVT4g-QSOt.gif) ## 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