This article is about the Synthesizer V Studio software known as a voice database. If you are looking for the Synthesizer V concept then click here.
History[]
On October 3, 2023, Dreamtonics Co., Ltd. posted a thread on Twitter announcing four new voice databases in development for Synthesizer V Studio that were to be "coming up", providing no information apart from teasers.[1] The second of four voice databases to be teased with a demo song within the thread was Eri, described as a "Japanese female voice database with a breathy, velvety decadence, most distinctive in the lower tones" and featuring "effortless transitions, ranging from a catchy, pop middle range to a powerful falsetto" intended "for melodic compositions".[2]
Eri was released on October 26, 2023.
Updates[]
Voice Database Information[]
Demonstrations[]
Demonstrations | |
---|---|
| |
Not yet | YouTube bilibili |
Not yet - Full version | YouTube bilibili |
Voice Databases[]
- Eri's voice was described as having a breathy, velvety decadence, most distinctive in the lower tones, as well as effortless transitions, ranging from a catchy, pop middle range to a powerful falsetto.
- She was noted to be suitable for melodic compositions.
- With Diffusion Probabilistic Models (DPM), Eri can sing more realistically through changes in volume and breath, further enriching singing details, making each singing unique, and providing creators with more options. Through this mode, she can use AI Retakes to create multiple "takes" of a sung section to find an ideal vocal without the need for "laborious tuning". This feature is only available in the Synthesizer V Studio Pro Editor.
- Phoneme format: Romaji
- Through Cross-lingual Singing Synthesis, Eri can sing in not only Japanese but also in English, Mandarin Chinese, and Cantonese Chinese. Since the release of her v101b1 update on December 18, 2023, she can also sing in Spanish with this feature. Cross-lingual Singing Synthesis is only available in the Synthesizer V Studio Pro Editor.
- Eri comes with four variations:
- "Aggressive"
- "Focused"
- "Relaxed"
- "Singing"
- It should be noted that the Vocal Modes were uniquely calibrated for diverse rap performances and work best in Eri's Rap Mode.
- Dreamtonics Co., Ltd.'s End User License Agreement - Japanese
- Dreamtonics Co., Ltd.'s End User License Agreement - English
- Dreamtonics Co., Ltd.'s End User License Agreement - Simplified Chinese
- Regarding the Feature-Limited Trial version:
- Individuals may only publish their works created with Synthesizer V AI Eri (FLT) for non-commercial purposes.
- When publishing works created with vocal, "Synthesizer V AI Eri Feature Limited Trial" must be specified in credits.
- The vocal has the following restrictions:
- Track count: up to 1 track per project file.
- Supported languages: Japanese
- Output duration: up to 45 seconds
- Vocal Mode: not available
- AI Retake (Timbre): not available
- VST3/AU plugin: not available
- Eri AI Solfège:
- Vocal Mode Solfèges:
- "Aggressive":
- "Focused":
- "Relaxed":
- "Singing":
- "Aggressive":
- Vocal Mode Solfèges:
- Eri Rap Example:
References[]
- ↑ https://twitter.com/dreamtonics_en/status/1709116086644310260
- ↑ https://twitter.com/dreamtonics_en/status/1709116090981466442
- ↑ https://dreamtonics.com/synthesizer-v-studio-1-11-0b2-update/
- ↑ https://dreamtonics.com/synthesizer-v-studio-1-11-0-update/
- ↑ https://twitter.com/ahsoft/status/1775800933538320621/photo/4
- ↑ https://img.alicdn.com/imgextra/i1/54187543/O1CN01QhKu2L25akRYbLX4i_!!54187543.png - Eri initially did not have a range listed upon release. This was added to her Taobao product page as of March 15, 2024