Printto Magicbeat
PRINTmov's Main Vocal
Printto Magicbeat is originally an UTAU since 2014. He is known for his ability to sing in many languages. He can sing up to 7+ languages in UTAU. His first DeepVocal voice library is recorded in Thai. Later, his Japanese DeepVocal library got released in 2019.
Printto Magicbeat is also the first-ever DiffSinger voicebank capable of singing in Thai. His Thai dataset is publicly available here.
Printto Magicbeat latest DiffSinger voicebank supports Thai, English, and Japanese. The main language of the voicebank is Thai with the addition of English and Japanese XLS.
In the past, 26 Printto Magicbeat UTAU and 4 DeepVocal voicebanks were released. However, 9 UTAU (including 3 long-term support voicebanks) and 2 DeepVocal voicebanks are available to download.
Printto Magicbeat V4 offers four vocal modes—Solid, New Casual, Soft, and Adult featuring a high-quality audio file dataset. The enhanced audio quality marks a significant improvement over Printto Magicbeat V3.
The voicebank is in beta, experimenting a new language prefix method.
| Languages | Thai, English, Japanese, French, Korean, Chinese, and Spanish |
| Vocal Modes | Solid, New Casual, Soft, and Adult |
| System | Language Prefixes |
| Data Used |
Alex Floarea CSD (Relabeled by heta-tan) M4Singer (Relabeled by nobodyP) Namine Criss Ofuton P PetitMillefeuille PJS (Relabeled by Utautautau) TIGER Toshio Sasagawa Zephyre |
Printto Magicbeat V3 offers six vocal modes—Default, New Casual, Adult, Sweet, and Casual—along with support for additional languages, providing a greater versatility.
| Languages | Thai, English, Japanese, French, Korean, Chinese, and Spanish |
| Vocal Modes | Default, New Casual, Sweet, Adult, Sweet, and Casual |
| System | Normal (Multi‑dictionary in the previous versions) |
| Data Used |
Alex Floarea CSD (Relabeled by heta-tan) M4Singer (Relabeled by nobodyP) Namine Criss Ofuton P PetitMillefeuille PJS (Relabeled by Utautautau) TIGER Toshio Sasagawa Zephyre |
Printto Magicbeat Millefeuille Edition is a DiffSinger voicebank trained by UFR. The model is based on Printto TH Dataset (v24.08.05). This voicebank supports 12 languages following Millefeuille's XLS standard.
Thanks to UFR’s training, this model features the most refined pitch model among all Printto Magicbeat voicebanks.
| Languages | Chinese, English, French, German, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, and Thai |
| Vocal Modes | Default and Casual |
| System | Multi-dictionary |
| Data Used | Millefeuille XLS Credits |
Printto Magicbeat V2 voice library for OpenUTAU supports 4 languages; Thai, English, Japanese, and Chinese in 1 voice library.
| Languages | Thai, English, Japanese, and Chinese |
| Data Used | TIGER, PJS, Ofuton P, and M4Singer |
Printto Magicbeat Thai V2 is the first version of Printto Magicbeat Thai AI with Thai characters fully compatible.
The voice library supports OpenUTAU's "tension" curve adjustment.
| Languages | Thai |
| Data Used | No additional data used. |
Printto Magicbeat Japanese ENUNU voice library for OpenUTAU.
| Languages | Thai, English, Japanese, French, Chinese, and Spanish |
| Vocal Modes | Alter and Adult |
| System | Language Prefixes (with TPSE) |
| Data Used |
Alex Floarea M4Singer (Relabeled by nobodyP) Namine Criss Ofuton P PetitMillefeuille PJS (Relabeled by Utautautau) TIGER Toshio Sasagawa Zephyre |
Author's Note: This needs to be temporary placed here because there is no section for the LIPSync Studio project yet. The software was initially developed for Printto Magicbeat.
The
dedicated page for LIPSync Studio will be available soon.
Please ensure that you read the README.txt file provided with the downloaded voicebanks before using them. It contains important instructions and guidelines that must be followed.
