Terms of Use — Amitaro’s Voice Material Studio
These materials are NOT public domain, CC0, or “do whatever you want” free
assets. All use is subject to the terms below. Please read carefully before
using.
If you can read Japanese, please refer to the Japanese terms of use.
日本語が読める方は、必ず日本語版の利用規約をご参照ください。
Amitaro’s Voice Material Studio provides free voice materials to support
creators of all kinds. All materials are intended for wholesome, all-ages use,
and these terms are designed to keep them that way.
What These Terms Cover
These terms apply to all audio materials and models freely distributed by
Amitaro’s Voice Material Studio.
| Material Type | Primary Uses |
|---|---|
| Voice clips | Games, videos, and apps |
| Live stream recordings | AI model training, voice synthesis |
| Corpus recordings (ITA corpus, etc.) | AI model training, voice synthesis |
| RVC models | AI voice changer, voice synthesis |
| Voice synthesis models (COEIROINK, SHAREVOX, etc.) | Text-to-speech, singing synthesis |
| UTAU voicebank (Koharune Ami) | Singing synthesis |
If you are using these materials through an external service, please also refer
to that service’s terms of use.
What Is Permitted
The following uses are permitted:
- Personal and commercial use, including monetization
- Use for any purpose — games, videos, apps, software, research, and more
- Editing, trimming, pitch-shifting, and other audio modifications
- Using the voice as a character voice for original characters, game characters,
virtual avatars, and similar creative works - Using as training data to create your own AI or voice synthesis models
(see AI Voice Models) - Integrating into software or games, where voice files cannot be independently
extracted by end users
Credit is required. See Credit Requirements below.
What Is Prohibited
Distribution
- Redistributing, reselling, or sharing voice files as a standalone collection,
whether free or paid - Bundling voice files in any format where end users can independently extract
or download them - Distributing or sharing AI voice models created from these materials
- Copying the voice clip script text to record and distribute in another voice
Content
- Any content not appropriate for children (sexually explicit content, adult
themes, etc.) - Works where grotesque or violent content is the primary focus
- Hate speech, harassment, or content that discriminates against individuals
or groups - Political or religious activity
- Advertising for gambling, alcohol, drugs, or weapons
Deceptive or harmful use
- Fraud, deception, or any use intended to deceive others
- Deepfake audio — making it appear a real person said something they did not say
- Automated voice fraud (vishing), robocall scams, or similar deceptive automated
calls - Using the voice as if it were your own natural voice
Rights and registration
- Registering raw voice materials or recordings in YouTube Content ID or any
equivalent rights-claiming system - NFT projects, blockchain-based assets, or cryptocurrency projects involving
these materials - Submitting works to competitions or contests where copyright transfers to the
organizer upon submission - Direct linking (hotlinking) to audio files hosted on Amitaro’s servers
- Using the names “Amitaro,” “Koharune Ami,” or “Amitaro’s Voice Material Studio”
to imply that a work is officially endorsed or created by Amitaro
Credit Requirements
Credit is mandatory. You must include “Amitaro’s Voice Material Studio
(https://amitaro.net/)” or “Koharune Ami” in a clearly visible location.
| Use | Credit format |
|---|---|
| Voice clips or recordings | Voice: Amitaro's Voice Material Studio (https://amitaro.net/) |
| Official RVC model | RVC Model: Amitaro's Voice Material Studio (https://amitaro.net/) |
| COEIROINK output | COEIROINK: Amitaro (https://amitaro.net/) |
| SHAREVOX output | SHAREVOX: Amitaro (https://amitaro.net/) |
| AI model training data | Training data: Amitaro's Voice Material Studio (https://amitaro.net/) |
| UTAU voicebank (Koharune Ami) | UTAU: Koharune Ami |
| Post on X (formerly Twitter) | Mentioning @amitaro_voice counts as credit for that post |
If a clickable link is not possible (video, print, etc.), a plain-text URL is
acceptable.
In environments where text credit cannot be included (VRChat, voice chat, etc.):
written credit may be omitted. However, if anyone asks about the voice, you must
clearly state that you are using voice materials from Amitaro’s Voice Material
Studio. Do not claim it is your natural voice.
Age & Content Restrictions
All uses must be appropriate for children of all ages, regardless of official
age ratings.
Sexually explicit content is strictly prohibited. There are no exceptions.
Violence that is not the primary focus of a work — such as combat sounds in a
game — is permitted. Works where grotesque or violent content is the primary
focus are not permitted.
AI Voice Models
Training on these materials to create your own AI or voice synthesis models
is permitted. All content restrictions above apply.
Official models distributed by Amitaro’s Voice Material Studio may not be
redistributed or resold.
Distributing or sharing any AI voice model, RVC model, or voice synthesis model
created from these materials is prohibited.
If using a self-trained model as a personal voice changer:
- Credit is required
- Do not use the names “Amitaro,” “Koharune Ami,” or “Amitaro’s Voice Material
Studio,” or any name that could be associated with them, for the model or its
output. This is to prevent confusion with official releases and statements by
Amitaro’s Voice Material Studio.
For academic research use, contact Amitaro in Japanese.
Recording Environment
A-weighted SPL: 18.5 dB
(Rion, NL-52EX)
Reverberation Time (T60): 220 ms
Note: T60 is estimated based on the method in [1]. The impulse response is introduced by Time-stretched pulse (TSP) [2].
Sampling frequency is 48 kHz, and quantization bit is 24 bit.
The duration of TSP is 524288 sample (10.92 s).
References
[1] M. R. Schroeder,”A new method of measuring reverberation time”,J. Acoust. Soc. Am.,vol. 37,pp 409−412,1965.
[2] N. Aoshima,”Computer-generated pulse signal applied for sound measurement”,J. Acoust. Soc. Am.,No. 69,vol. 5,1981.
Contact & Inquiries
→ FAQ: https://amitaro.net/voice/terms/faq_en/
All inquiries must be submitted in Japanese. Inquiries in English or other
languages will not receive a response.
Lack of response does not constitute approval, permission, or acknowledgment
of any use not already permitted by these terms.
Governing Law & Disclaimer
These terms are governed by the laws of Japan.
These materials are provided “as is,” without warranty of any kind. Use is at
the user’s own risk.
Use of these materials does not imply endorsement or approval by Amitaro’s Voice
Material Studio of any work, product, or creator.
Please also comply with the laws of your region and the terms of any platform
where you publish.
If a violation of these terms is confirmed, we may request that you discontinue
use.
Changes to These Terms
These terms may be updated without prior notice. Major changes will be announced
on X @amitaro_voice (https://twitter.com/amitaro_voice).
Changes to these terms do not affect works created and published before the
update was made.
Last updated: 2026-06-01
Support This Project
Amitaro’s Voice Material Studio offers native Japanese kawaii anime girl voice assets, free for creators worldwide.
This project is run on a volunteer basis, so that you can bring your creations to life with a real voice.
If you use these voice assets, sharing your work, spreading the word, or linking back to this site means a lot.
If you’d like to support the project, Ko-fi donations are greatly appreciated — they help cover server costs and equipment, and keep new assets coming for future creators.

