Synthesizer V Studio 1.10.0b2 Update
Dreamtonics releases Synthesizer V Studio 1.10.0b2.
This second beta version following our August release of 1.10.0b1 introduces enhancements to voice databases, integrating the latest user feedback through Reinforcement Learning from Human Feedback (RLHF). On the editor side, numerous issues reported by our users have been addressed for an even more fluid experience.
Synthesizer V Studio 1.10.0b2 can be accessed via the download links provided at the end of this document. To enjoy the improvements made to the pitch and timbre models, please manually download the latest beta version of the voice databases.
Feedback-Enhanced Pitch Models
Our previous 1.10.0 beta introduced a redesigned pitch generation system grounded in RLHF, featuring a built-in mechanism for users to weigh in on singing expressions by choosing their preferred take. Thanks to the extensive feedback shared by the participating beta users over the past month, we’ve trained a new generation of pitch models. These models excel at handling specific skills, such as transitions and vibratos, aligning more closely with the genuine requirements of vocal production.
Refined Voice Timbre
Moving beyond pitch enhancements, our new models offer greater accuracy in voice timbre reproduction, coupled with a reduction in mispronunciations. Notably, we’ve tackled issues from the previous beta release that made vocal modes appear less distinct on some voices, ensuring clearer differentiation in the latest update.
More Usability Improvements
Syllable Division Made Easy
The 1.10.0b2 update introduces a new feature within the Note Properties Panel that allows for even division of a note into multiple syllables. Although many compositions typically assign one syllable per note, this feature proves useful for faster-paced songs. It aids in quickly filling in lyrics while maintaining rhythm synchronization, especially beneficial when screen space is limited.
As Synthesizer V Studio has evolved, the Piano Roll toolbar began to feel increasingly congested. To simplify this, we’ve made an intuitive UI adjustment: when space becomes limited, visualization options will seamlessly transition into a popup menu, preserving a clutter-free workspace.
How to Access the New Release
Separate beta versions will be released for both Synthesizer V Studio and the voice databases.
Synthesizer V Studio 1.10.0b2
1.10.0b2 is a beta version. Beta releases of Synthesizer V Studio are offered before the final release for early preview of new features. Before installing and using a beta version, please understand that:
- The beta version is still a work in progress.
- The beta version may not function properly as described.
- Unexpected behaviors may happen while using the beta version.
You can access the beta versions for Synthesizer V Studio through the download page.
We are offering beta updates for the following voice databases:
|Dreamtonics||An Xiao, Cheng Xiao, Cong Zheng, D-Lin, Feng Yi, Kevin, Lin Lai, Mai, Mo Chen, Natalie, Ninezero, Ritchy, Ryo AI, Saki AI, Qing Su, Weina, Xuan Yu, Yuma, Yun Quan|
|AHS||Tsurumaki Maki AI (JPN), Tsurumaki Maki AI (ENG), Kyomachi Seika AI, Tsuina-Chan AI, Kasane Teto, Koharu Rikka AI, Natsuki Karin AI, Hanakuma Chifuyu AI, Haruno Sora|
|Animen||Eleanor Forte AI|
|E-Capsule||Xia Yu Yao|
|Eclipsed Sounds||SOLARIA, ASTERIAN|
You can access the beta versions for these voice databases through the download page.
See below for detailed release notes.
Synthesizer V Studio 1.10.0b2 (Sep 28, 2023)
- Auto-Process: added support for RLHF-enhanced pitch models with the addition of “Enhancement” parameter on pitch takes (Voice Database update required).
- Arrangement: added a track color selector to the right-click menu on track headers.
- Piano Roll: added a menu item for shifting forward/backward the lyrics of the selected notes.
- AI Retakes Panel: users may opt-in retake feedback collection that sends the “liked” takes along with surrounding notes and other project data to Dreamtonics for improving the sound quality.
- Note Properties Panel: added a new option “Evenly split note into syllables” for notes with multi-syllable lyrics. (Update from 1.10.0b1)
- Synthesizer V Engine: improved the generation of phoneme duration and diversified the effect of timbre retakes (Voice Database update required).
- AI Retakes Panel: redesigned the panel to always display the global (track or group-level) values for Expressiveness and Enhancement.
- Plugin: AU and VST3 plugins now support drag-and-drop importing of MIDI files.
- Misc: improved activation server connectivity from Mainland China.
- GUI: hide some of the visualization options from the piano roll when there’s insufficient horizontal space. (Update from 1.10.0b1)
- AI Retakes Panel: Expressiveness and Enhancement sliders in the take list now display absolute values (after summing with the global Expressiveness/Enhancement) instead of the offset.
- File: disabled forward-compatibility for projects saved in Synthesizer V Studio 1.10.0 and onwards due to a breaking change in the value range of take Expressiveness. Users may use “File/Save As (1.9.0-Compatible)…” to export the project to an earlier version of Synthesizer V Studio.
- Synthesizer V Engine: fixed crashes and quality degradation on standard voice databases due to some dictionary changes introduced in the last update.
- GUI: fixed missing fonts on some keyboard shortcuts on macOS.
- Live Render: fixed a bug causing the renderer to skip some parts of a project when loaded immediately after startup.
- Auto-Process: fixed a bug where pitch computation inside note groups leaves unwanted fluctuations in the pitch curve. (Update from 1.10.0b1)
- Live Render: fixed crashes when loading an unsupported voice database. (Update from 1.10.0b1)
- Linguistics: fixed muted notes when a legato follows a note in Japanese that begins with a manually specified “cl” phoneme. (Update from 1.10.0b1)
- Linguistics: fixed the overriding of manually specified phonemes by “Use relaxed consonants” option. (Update from 1.10.0b1)
- Plugin: fixed broken compatibility with some DAWs on Windows. (Update from 1.10.0b1)
- Plugin: fixed playback synchronization issues after bouncing audio from certain DAWs when using the AudioUnit plugin. (Update from 1.10.0b1)
- AI Retakes Panel: fixed the display location of popup messages before submitting feedback for the first time. (Update from 1.10.0b1)
- AI Retakes Panel: fixed the display of expressiveness on take items when OpenGL is on. (Update from 1.10.0b1)
- GUI: fixed unintended layout reset after exiting the editor with Arrangement Panel folded beneath the Piano Roll. (Update from 1.10.0b1)