2022.11.10

Synthesizer V

Synthesizer V Studio 1.8.0b1 Update

Dreamtonics releases the Synthesizer V Studio 1.8.0b1 update.

As a major and comprehensive update, 1.8.0b1 is being rolled out as a beta first. The update introduces a major evolution of the synthesis engine – high speed Diffusion Probabilistic Models (DPM) based singing synthesis technology, along with a number of exciting features and improvements detailed below.

1.8.0b1 also introduces MIDI keyboard and metronome support. Cross-lingual Synthesis feature gets updated to support note-level specification of the language.

Users are invited to update individual voices to give the new engine a try. You will find the full list of voices, currently available for updating, down below.

In addition to the voice updates, on Oct 27 Dreamtonics released the demo for a new Japanese voice database, Synthesizer V AI Mai. We are happy to announce today that users who have purchased the Synthesizer V Studio Pro version will have access to Mai for free.

Diffusion Probabilistic Models (DPM)

Synthesizer V Studio 1.8.0b1 integrated high speed Diffusion Probabilistic Models (DPM) based singing synthesis technology, which is a major evolution of the synthesis engine.

DPMs (sometimes shortened to as Diffusion Models) are used in image generation AIs. By overcoming several technical challenges, namely the stability and efficiency issues, Dreamtonics has now introduced the technology in Synthesizer V Studio.

The new DPM based synthesis engine sounds more natural and pronounces more accurately than ever before. It also becomes more pitch accurate, while exhibiting a use of more nuanced singing techniques, in particular improvements on vibratos.

Synthesizer V Studio 1.8.0b1 achieves an exceptional level of realism. In the research phase, Dreamtonics conducted extensive subjective listening tests to compare the new technology against the previous generations and human performance. In a test involving 20 participants designed to evaluate the timbre generation capabilities, statistically significant improvements from the previous generation models were found. In the same test, no statistically significant difference was found between DPM-rendered singing and the performance by humans.

Note: to use the new synthesis engine users must update the voice (see Voice updates for 1.8.0b1 below).

Voice updates for 1.8.0b1

As Synthesizer V Studio 1.8.0b1 is still in beta, users are invited to manually download and install the voices in order to enjoy the DPM feature.

Which voices are going to be updated

Dreamtonics	An Xiao, Feng Yi, Kevin, Mo Chen, Natalie, Ryo AI, Saki AI, Qing Su, Weina, Yuma
AHS	Koharu Rikka AI, Natsuki Karin AI, Hanakuma Chifuyu AI, Tsurumaki Maki AI (JPN), Tsurumaki Maki AI (ENG), Kyomachi Seika AI, Tsuina-Chan AI
AUDIOLOGIE	ANRI
Eclipsed Sounds	SOLARIA
Quadimension	MEDIUM5 Stardust
Animen	Eleanor Forte AI

You can download the installers from our download page .

Note: The beta version is no longer available due to the release of the final update.

Support for MIDI keyboards and metronome

Users can now connect a USB MIDI keyboard to Synthesizer V Studio (only supported in the Pro version) and click the record button to input notes in real-time.

The feature also includes a metronome option to help synchronize the performance with the beats.
1.8.0b1 also supports MIDI Machine Control (MMC), a feature supported by some keyboards that allows users to control Synthesizer V Studio using the play/pause/record buttons on their keyboards.
The new “Smart Quantization” feature helps clean up the notes entered from the keyboard.

Note-level cross-lingual synthesis

This feature allows songs with multilingual lyrics to be sung smoothly without having to separate tracks or groups, allowing switching languages while singing. The language of the notes can be set in the Language section of the Note Properties panel.

Synthesizer V AI Mai is now available and is free for Pro users

Dreamtonics releases Synthesizer V AI Mai as a free voice database for Synthesizer V Studio Pro users. Mai is released under the same licensing terms as other Dreamtonics voices, meaning no restriction on the monetization of songs created with Mai.

You may download the installer for Mai here.

New Synthesizer V Studio Page

The new Synthesizer V Studio product page is now updated to showcase all the latest features of the synthesizer.

Get Synthesizer V Studio 1.8.0b1

1.8.0b1 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.

Download Links

Synthesizer V Studio Pro

Synthesizer V Studio Basic

See below for detailed release notes.

Synthesizer V Studio 1.8.0b1 (Nov 10, 2022)

New Features

Synthesizer V Engine: support for voices based on Diffusion Probabilistic Models (DPM).
Piano roll: support for real-time MIDI input. (MIDI keyboard required, Pro version only)
Piano roll: support for MIDI Machine Control (play, stop, record, fast-forward, fast-rewind). (Pro version only)
Piano roll: add metronome. (Pro version only)
Note Properties Panel: add note-level cross-lingual synthesis. (Pro version only)
Modify menu: add “Smart Quantization” feature.

Enhancements

GUI: updated dialog designs.
Piano roll: adjusted note dragging behavior to prevent misclicks.
AI Retakes: UI adjustments for AI Retakes Expressiveness slider.
File: the default name for “Save As…” has been changed to the project name.

Bug Fix

File: fixed corrupted lyrics when loading a MIDI file with unicode lyrics.
Auto-Process: fixed crashes when switching projects before Instant Mode finishes processing.
Synthesizer V Engine: fixed a bug where the voice is not completely muted when loudness parameter is set to the minimum.

Misc

Removed the support for 32-bit Windows.