My Project

Appearance

A Few Words Before Downloading 👋 ​

If you came here by searching for Voiceger, I’d suggest trying the official version first. Every piece of software has its own strengths, but the original release delivers its authentic flavor. Any seasoning you add later will still depend on the original ingredients. > Official Original Download Link Here

Even if the voice source is generated with this software, please tag it directly as Voiceger:Zundamon. Do not use the VoicegerN:Zundamon tag.
I am not responsible for any violation of the rules.

Note: The AI features use Qwen3TTS by default. Please do not delete Qwen3TTS.

AI features require you to obtain an API key from the DeepSeek API platform. This software does not include or provide any API keys.

To conserve tokens, we kindly ask that you refrain from frequently initiating new conversations.

We will release the source code no later than the end of September. We apologize for the delay.

https://www.karylzdm.xyz/VoicegerN_EN/

OneDrive: https://1drv.ms/f/c/2515a955332b8d21/IgAYnMHvz79NTp92D-xLlt33AaeKnEQHGSjtR6CwLDOjo2M?e=h9kJOF
GoogleDrive: https://drive.google.com/drive/folders/1D1hyP7-uNu-LBbslzurPixuonYXyn7vJ
yukaidi: https://silver.yukaidi.com/s/dEJqC5/nanoda
huang1111: https://pan.huang1111.cn/s/RYvEPiB

If download speeds are slow, feel free to use an alternative downloader.

Terms of Use (Voiceger:Zundamon) ​

The content below is sourced from https://zunko.jp/con_ongen_kiy.html. Please abide by these terms.

  1. This resource may be used for both commercial and non‑commercial purposes.
  2. You must comply with the common terms for this voice source.
  3. You must add the copyright attribution Voiceger:Zundamon near any published audio generated with this resource (attribution may be written in other languages).
    If you cannot place the attribution directly beside the audio, provide it on a supplementary web‑page or equivalent location.

Prohibited Uses (Use of this voice source is forbidden for the following cases) ​

  1. Use that violates public order and good morals
  • Do not use for content contrary to social ethics and public order.
  1. Political or religious purposes, or content attacking / endorsing specific individuals or groups (including nations)
  • Do not use for political activities, religious activities, or activities that may lead to them.
  • Do not use this voice source to condemn, criticize, or advocate for any specific individual or group (including nations).

In short: Do not use this AI voice for taking sides, debates, partisan propaganda, or religious preaching.

  1. Use related to so‑called information‑based commercial products
  • Do not use the voice source within information‑based commercial products, nor use it to advertise such products.

"Information‑based commercial products" refers to the Japanese‑concept of high‑priced paid courses, get‑rich schemes, and similar knowledge‑sale offerings, many of which exist within a grey‑market space.

  1. False or fake information
  • Do not use this voice source to create, share, or spread deliberately false or misleading content.

Do not use this voice to produce fake‑news or defamatory audio.

  1. Use within adult‑entertainment‑related business categories
  • Under Japan’s Entertainment Business Act:
  • Use is prohibited for Category‑1, 2, 3 host‑restaurant‑style businesses, as well as special businesses related to sexual entertainment.

Simply put: Use is strictly forbidden for pornography, host‑service‑style adult‑entertainment industries.

  1. Any use connected to anti‑social forces
  • The following parties are prohibited from using this voice source:
  • Yakuza‑related groups, gang members, associate members, gang affiliates, sokaiya racketeers, groups extorting under the guise of social activism, special intelligent violent groups, and all other anti‑social organizations.
  • Also prohibited: Use by any individual or organisation that collaborates with, participates in, or exploits anti‑social forces.

Also prohibited are the following acts: Violent demands, unreasonable demands exceeding legal obligations, threatening language or physical violence; spreading rumours, using fraud or intimidation to damage another party’s reputation or interfere with business operations.
If any of the above‑mentioned prohibited usages occur, all usage licences for the offending individual or organisation will be revoked.

Disclaimer ​

  1. The copyright‑holder accepts no liability whatsoever for any damages arising from goods, services or transactions that make use of this voice source. All risks shall be borne entirely by the user.
  2. In‑principle, inquiries asking whether a given use complies with these guidelines will not be answered.
  • In particular, enquiries regarding the scope of free‑of‑charge usage will not receive a reply (as manpower costs would be incurred to answer questions for a free resource).
  • Users are expected to read these guidelines carefully and make their own judgement regarding compliance of their intended use‑case.

Acknowledgments 🙏 ​

  • Official voice sources and RVC models
  • Qwen3TTS GGUF and Safetensors models, and VoxCPM2 GGUF models
  • Authors of RVC
  • MiSans (included for better appearance 😊)
  • GitHub open‑source projects and source code used in development (e.g., FFmpeg, VITS used in RVC, etc.)

Official voice source: https://github.com/zunzun999/voiceger_v2
Official RVC model: https://huggingface.co/zunzunpj/zundamon_RVC

Qwen3TTS GGUF model: https://huggingface.co/Serveurperso/Qwen3-TTS-GGUF

Qwen3TTS Safetensors model:

Download link: https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-Base

VoxCPM2 GGUF model:

Download link: https://huggingface.co/DennisHuang648/VoxCPM2-GGUF

RVC author: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI

MiSans: https://hyperos.mi.com/font

Various GitHub open‑source projects can be found in the repositories listed above (e.g., third‑party licenses, etc.).