ModelListedExternal

Step Fun EditX

Files Needed for Vantage-Step-Audio-EditX ComfyUI node

Sourcehuggingface.co/vantagewithai/Step-Fun-EditX-ComfyUI/tree/ac52334fcfe05ba1f20426f4b470f4220576998c

KindText modelVersionmodelCgrade

Model source

Kind: Text model
File size: 6.57 GB
Version: vmodel
Updated: Oct 2, 2026
Downloads: 0
Source: Hugging Face

Source description

Step-Audio-EditX

Files Needed for Vantage-Step-Audio-EditX ComfyUI node

Original Model Link: https://huggingface.co/stepfun-ai/Step-Audio-EditX

Watch us at Youtube: @VantageWithAI

🌟 ComfyUI Node

After downloading the models, copy them into ComfyUI/models, you should have the following structure:

ComfyUI/
├── models/
│   ├── Step-Audio-EditX/
│   ├──── CosyVoice-300M-25Hz/
│   │     ├─── campplus.onnx
│   │     ├─── cosyvoice.yaml
│   │     ├─── flow.pt
│   │     └─── hift.pt
│   ├──── dengcunqin/
│   ├──── └─── speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/
│   │          ├─── am.mvn
│   │          ├─── config.yaml
│   │          ├─── configuration.json
│   │          ├─── model.pt
│   │          ├─── seg_dict
│   │          ├─── tokens.json
│   │          ├─── tokens.txt
│   │          └─── write_tokens_from_txt.py
│   ├── model.safetensors
│   └── speech_tokenizer_v1.onnx

Features

Zero-Shot TTS
- Excellent zero-shot TTS cloning for Mandarin, English, Sichuanese, and Cantonese.
- To use a dialect, just add a [Sichuanese] or [Cantonese] tag before your text.
Emotion and Speaking Style Editing
- Remarkably effective iterative control over emotions and styles, supporting dozens of options for editing.
  - Emotion Editing : [ Angry, Happy, Sad, Excited, Fearful, Surprised, Disgusted, etc. ]
  - Speaking Style Editing: [ Act_coy, Older, Child, Whisper, Serious, Generous, Exaggerated, etc.]
  - Editing with more emotion and more speaking styles is on the way. Get Ready! 🚀
Paralinguistic Editing:
- Precise control over 10 types of paralinguistic features for more natural, human-like, and expressive synthetic audio.
- Supporting Tags:
  - [ Breathing, Laughter, Suprise-oh, Confirmation-en, Uhm, Suprise-ah, Suprise-wa, Sigh, Question-ei, Dissatisfaction-hnn ]

For more examples, see demo page.

Citation

@misc{yan2025stepaudioeditxtechnicalreport,
      title={Step-Audio-EditX Technical Report}, 
      author={Chao Yan and Boyong Wu and Peng Yang and Pengfei Tan and Guoqiang Hu and Yuxin Zhang and Xiangyu and Zhang and Fei Tian and Xuerui Yang and Xiangyu Zhang and Daxin Jiang and Gang Yu},
      year={2025},
      eprint={2511.03601},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2511.03601}, 
}

Sources

1 source

Hugging FacePrimaryVersion ac52334fcfe05ba1f20426f4b470f4220576998c

huggingface.co/vantagewithai/Step-Fun-EditX-ComfyUI/tree/ac52334fcfe05ba1f20426f4b470f4220576998c

Verified Oct 2

Model artifacts

1 artifact

Step-Audio-EditX/model.safetensors

safetensors · 6.57 GB · SHA-256 52004bb64a1f…d7b3 · Hugging Face

Download

Source excerpts

2 excerpts

ReadmeJul 17huggingface.co/vantagewithai/Step-Fun-EditX-ComfyUI

--- license: apache-2.0 pipeline_tag: text-to-speech library_name: transformers --- ## Step-Audio-EditX **Files Needed for Vantage-Step-Audio-EditX ComfyUI node** **Original Model Link:** [https://huggingface.co/stepfun-ai/Step-Audio-EditX](https://huggingface.co/stepfun-ai/Step-Audio-EditX) **Watch us at Youtube:** [@VantageWithAI](https://www.youtube.com/@vantagewithai) 🌟 [ComfyUI Node](https://github.com/stepfun-ai/Step-Audio-EditX) After downloading the models, copy them into ComfyUI/models, you should have the following structure: ``` ComfyUI/ ├── models/ │ ├── Step-Audio-EditX/ │ ├──── CosyVoice-300M-25Hz/ │ │ ├─── campplus.onnx │ │ ├─── cosyvoice.yaml │ │ ├─── flow.pt │ │ └─── hift.pt │ ├──── dengcunqin/ │ ├──── └─── speech_paraformer-large_asr_nat-zh-cantonese-en-16k-vocab8501-online/ │ │ ├─── am.mvn │ │ ├─── config.yaml │ │ ├─── configuration.json │ │ ├─── model.pt │ │ ├─── seg_dict │ │ ├─── tokens.json │ │ ├─── tokens.txt │ │ └─── write_tokens_from_txt.py │ ├── model.safetensors │ └── speech_tokenizer_v1.onnx ``` ## Features - **Zero-Shot TTS** - Excellent zero-shot TTS cloning for Mandarin, English, Sichuanese, and Cantonese. - To use a dialect, just add a **[Sichuanese]** or **[Cantonese]** tag before your text. - **Emotion and Speaking Style Editing** - Remarkably effective iterative control over emotions and styles, supporting **dozens** of options for editing. - Emotion Editing : [ *Angry*, *Happy*, *Sad*, *Excited*, *Fearful*, *Surprised*, *Disgusted*, etc. ] - Speaking Style Editing: [ *Act_coy*, *Older*, *Child*, *Whisper*, *Serious*, *Generous*, *Exaggerated*, etc.] - Editing with more emotion and more speaking styles is on the way. **Get Ready!** 🚀 - **Paralinguistic Editing**: - Precise control over 10 types of paralinguistic features for more natural, human-like, and expressive synthetic audio. - Supporting Tags: - [ *Breathing*, *Laughter*, *Suprise-oh*, *Confirmation-en*, *Uhm*, *Suprise-ah*, *Suprise-wa*, *Sigh*, *Question-ei*, *Dissatisfaction-hnn* ] For more examples, see [demo page](https://stepaudiollm.github.io/step-audio-editx/). ## Citation ``` @misc{yan2025stepaudioeditxtechnicalreport, title={Step-Audio-EditX Technical Report}, author={Chao Yan and Boyong Wu and Peng Yang and Pengfei Tan and Guoqiang Hu and Yuxin Zhang and Xiangyu and Zhang and Fei Tian and Xuerui Yang and Xiangyu Zhang and Daxin J...

NoteJul 17huggingface.co/vantagewithai/Step-Fun-EditX-ComfyUI

Source context: 0 downloads · 2 likes · Pipeline text-to-speech · Library transformers · Repo vantagewithai/Step-Fun-EditX-ComfyUI