Dreamtonics releases Synthesizer V Studio 2 Pro

Dreamtonics has announced the release of Synthesizer V Studio 2 Pro, a major update to its flagship singing voice synthesis application.

Unveiled at NAMM 2025, Synthesizer V Studio 2 Pro is now available, offering significant improvements in sound quality and speed, as well as new features for fine-tuning singing voices.

New Features in Synthesizer V Studio 2 Pro

Watch the preview video for an in-depth look at the exciting new features in Synthesizer V Studio 2 Pro:

YouTube.com/watch?v=MU_7vgvRbkY

Enhanced Voice Quality and Dynamics

The updated models in Synthesizer V Studio 2 Pro more accurately replicate human-like voice dynamics, resulting in a greater sense of presence with finer details. This improvement is achieved without compromising on pronunciation and pitch accuracy. Additionally, the preserved dynamics enable AI Retakes to generate more diverse options, giving users more choices to achieve their desired pattern.

Massive Optimizations

Thanks to improved algorithm design and enhanced multi-threading support, Synthesizer V Studio 2 Pro renders up to 300% faster than its predecessor. This significant speed boost is achieved without requiring a dedicated GPU or acceleration hardware, allowing for seamless offline use.

Phoneme Timing Panel

The new Phoneme Timing panel allows for direct resizing and adjustment of phoneme intensity within a note. For certain consonants, the panel offers precise control beyond phoneme-level, enabling detailed adjustments to timing and prominence of plosive onsets.

Enhanced Vocal Modes

Upgraded Synthesizer V voices now feature more distinct Vocal Modes, with the ability to assign separate modes to pitch, timbre, and pronunciation. This allows users to create nuanced singing styles by combining different modes, such as pairing a "powerful" pitch with a "belting" timbre and a "soft" pronunciation. By decoupling these elements, users can craft significantly more realistic, emotionally expressive vocals that perfectly suit the tone and style of their music.

Expression Pad and Timing AI Retakes

AI Retakes is now integrated into the Notes panel, allowing for single-click retakes of phoneme timing in addition to existing functionality. The Expression Pad offers a convenient way to modulate pitch generation behavior.

Smart Pitch Controls

The new Smart Pitch Controls system enables users to quickly and intuitively shape pitch expressions with precision. By inputting key locations for desired pitch changes, the system generates natural-sounding curves that accurately reflect the user's intentions in near real-time. This intuitive tool allows regular users to achieve nuanced pitch expressions with minimal editing, while also empowering power users to create complex, realistic singing styles.

Mouth Opening Parameter

A new parameter, the first of its kind, has been added to upgraded voices: Mouth Opening, which fundamentally alters vowel pronunciation. This intuitive control allows users to accentuate specific words, or subtly modify the way a phrase begins or ends, adding depth and expressiveness to their synthesized vocals.

Korean Support

Synthesizer V Studio 2 Pro introduces support for Korean as a new voice synthesis language. Additionally, Korean will be available as a cross-lingual synthesis language option for all upgraded voices.

New Complimentary Voices

Synthesizer V Studio 2 Pro includes a complimentary voice which can be chosen from the following options:

• Mai 2: The upgraded version of Mai, the Japanese female voice bundled with Synthesizer V Studio Pro version 1.
• Liam: Dreamtonics' new male classic Pop/Rock voice native in English.
• Mo Xu: Dreamtonics' new female R&B voice native in Mandarin.

YouTube.com/watch?v=MBI8AM19rU8

YouTube.com/watch?v=9mxEu2qL9xU

Pricing & Availability

Synthesizer V Studio 2 Pro is available now for $99.

Until April 20th, 2025, all Dreamtonics version 2 voices (except Weina) are available for $69, a discount from the regular price of $79.

Upgrades from Synthesizer V Studio 1 and version 1 voices are available.