ESpeak is an open-source software speech synthesizer. Multiple languages are provided to users in smaller sizes as these tools use a formant synthesis method. The voice output generated through. Speech synthesis basically translates written information into aural information using a machine-generated voice. It is best for learning foreign languages, for visually impaired people wherein the contents on the screen can be read out loud for them. Some of the prominent examples of speech synthesizers are Alexa, Cortana, and Google Home.

New Generation AI Singing Voice Synthesis Software
Synthesizer V AI
Expected Arrival Early 2021

Tokyo-based Dreamtonics (representative: Kanru Hua) announces support for fully deep learning based singing voice synthesis coming to Synthesizer V in early 2021. A free update will be available for Synthesizer V Studio Pro.

Dreamtonics is the developer of Synthesizer V, a cross platform (Windows / Mac / Linux) singing voice synthesis software. The upcoming deep learning upgrade will push voice quality to a level nearly indistinguishable from that of a real human singer. Seamless switching between regular voices and AI voices will be incorporated into the existing interface.

Dreamtonics also announces an AI version of Synthesizer V Saki voice database, which is currently on sale through AHS Co., Ltd. (Tokyo-based, representative: Tomohide Ogata). AHS will offer the AI version for free to current users of Synthesizer V Saki during a limited period. In regards to Koharu Rikka voice database currently under development, in addition to the standard voice database, an AI version is also to be released by Spring 2021.

Synthesizer V Studio Basic (available through free download) will also become compatible with AI voices. Saki AI Lite, a slimmed down voice database will be made available free of charge. The pair offers a casual setup to try out deep learning based voice synthesis.

A crowdfunding event will be conducted in November for Synthesizer V AI and regular versions of Onikko Hunter Tsuina-chan, a VOICEROID currently on sale through AHS.

More details on Synthesizer V AI will be available on an AHS hosted YouTube event. We will be joined by Mr. Akasako (TOKYO 6 ENTERTAINMENT) directing the Koharu Rikka project.

Link: https://www.ah-soft.com/ustream/
Time: JST 20:00 October 30

Synthesizer V AI Voice Demo

More demos are available on Dreamtonics official Youtube channel.

Voice Synthesis Software

Related Links

AHS Co., Ltd. Official Website: www.ah-soft.com

About Synthesizer V

Synthesizer V is a voice synthesis software developed by Dreamtonics that combines a powerful voice processing engine with an intuitive and flexible user interface. Users can create an original song simply by drawing a melody and filling in lyrics.

Free Voice Synthesis Software

About Synthesizer V Saki

Voice Synthesizer

Synthesizer V Saki is a Japanese voice database sampled from a talented singer songwriter. Created directly by Dreamtonics, Saki is the first voice based on a refined generation of singing synthesis technology and is considered an official reference voice demonstrating the software’s new features.

About Dreamtonics

Voice Synthesis Software

Dreamtonics is a Tokyo-based startup specializing in electronic music and voice technology. We build and provide the best music software to meet your creativity needs.
For corporate customers, we also provide services such as technology licensing and artificial voice creation.

Contact

Dreamtonics Co., Ltd.
Address: 501 Otomi Building. 5-8-11 Asakusabashi. Taito-ku. Tokyo 111-0053.
E-mail: inquiry@dreamtonics.com
Website: dreamtonics.com