Synthesizer V is a music software and a sample-based speech synthesizer consisting of two generations. The second generation of the synthesizer combines traditional and new vocal synthesis models using artificial intelligence.

The program does not require complex manipulations from users and can transition from ordinary samples to an accurate recording of the human voice while working. This software is available for macOS-based devices.

Samples

Samples with the voice of virtual singers are located in files with the "svpk" extension. The total number of voices available in the second synthesizer generation is ten. There are two female Japanese voices, one male Japanese voice, one English female voice, one male Chinese voice, and five female Chinese voices. The voice providers of Eleanor Forte and Saki are unknown because their voice samples are the exclusive property of the Dreamtonics company. It has signed a non-disclosure agreement with the voice providers.

What voices are available in the program?

Synthesizer V for Mac has many voices. The voices of the first and second generations of the Synthesizer include:

• Eleanor Forte is a virtual English-speaking singer with a voice sample codenamed ENG-F1. She is the only singer in Synthesizer V who sings songs in English. That's the reason for her popularity among computer music fans. According to users, her voice sounds so close to a natural person's voice that it can cause consternation at some stage of working. She is portrayed with silver hair in black and white clothes. The thread she holds in her hands is the red thread of fate, an element of Eastern myths. No recommendation for the range is given. User experiments have shown that Eleanor Forte can even sing complicated opera arias, such as the aria from "The Phantom of the Opera."

• Yamine Renry is a seventeen-year-old virtual singer who sings songs in Japanese. A singer with the pseudonym Yuzuri is her voice provider. Yamine Renry was introduced on September 28, 2014, as part of the UTAU engine. She became available for use in Synthesizer V on November 11, 2018. A voice sample for the second generation of Synthesizer is in development.

• Genbu is a virtual singer who sings songs in Japanese. A singer with the pseudonym Gallo is his voice provider. He was released on December 23, 2018, and upgraded to a second-generation synth on July 15, 2020.

• Aiko is a sixteen-year-old virtual singer and the mascot of Animen. She is the first Chinese singer in Synthesizer V. Liang Xiao Miao is her voice provider. She was released on December 28, 2018. On July 15, 2020, it was updated to a second-generation synthesizer. No recommendation for the range is given.

• Chiyu is a seventeen-year-old virtual singer who sings songs in Chinese. A singer with the pseudonym Yumao is her voice provider. She was released on April 30, 2019. Chiyu represents the element of fire. A recommended range is low, first and the second octave. A recommended tonality in E-flat major in the first octave and B major in the minor octave. A major in the first octave and D major in the second octave for music with falsetto elements.

• Shian is a fourteen-year-old virtual singer who sings in Chinese and is Haiyi's younger sister. A singer with the pseudonym Varma is her voice provider. She was released on June 20, 2019. Shian represents the element of earth. A recommended range is E-flat major in the first octave, B major in the minor octave, A-flat major in the first octave, and C major in the second octave for music with falsetto elements.

• Cangqiong is an eighteen-year-old virtual singer who sings songs in Chinese, developed by Beijing Photek S&T Development Co., Ltd. She was released on June 9, 2019. Haiyi, Shian, and Chiyu are her younger sisters. Cangqiong represents the element of air. A recommended range is the first octave. A recommended tonality is F major in the first octave and C major, B flat major, and B major in the first octave for music with falsetto elements.

• Haiyi is a fifteen-year-old virtual singer who sings songs in Chinese. She is the younger sister of Chiyu. A singer with the pseudonym Huazheng Anly is her voice provider. She was released on September 6, 2019. Haiyi represents the element of water. A recommended range is E major in the first octave, C major, and A major in the first octave for music with falsetto elements.

• Saki is a virtual singer created for the web version of Synthesizer V. A voice provider is unknown. She was officially named only after the release of the second generation of the Synthesizer. She will be present in the third generation of Synthesizer.

• Akane & Aoi Kotonoha are a duo of virtual Japanese singers introduced as part of the VOICEROID engine. Yui Sakakibara is their voice provider. They were released in the second generation of Synthesizer on July 30, 2020.

• Muxin is a fourteen-year-old virtual singer who sings songs in Chinese. A singer with the pseudonym YuukaNeko is his voice provider. He was released on August 15, 2020;

• Stardust Minus;

• Rikka Koharu.

The voices of the third generation include:

• Maki Tsurumaki is a virtual singer who sings songs in Japanese and English. She was introduced as part of the VOICEROID engine and had two voice providers: Tomoe Tamiyasu in VOICEROID and Minami Tanaka in Synthesizer V;

• Seika Kyomachi is a twenty-three-year-old virtual singer who sings songs in Japanese. She was released on June 10, 2016, and was the mascot of Seika, a village in Kyoto Prefecture. Later she became a manga character and voice assistant. Seika was introduced as part of the VOICEROID engine due to crowdfunding, with the final amount exceeding the actual requirement. A new crowdfunding campaign created to release Seika as part of the third generation of Synthesizer V exceeded the required amount again;

• Tsuina-Chan.