The vocal synthesis software is gearing up for an official launch on 21 March. Tokyo-based music software and voice technology company Dreamtonics has announced the forthcoming release of Synthesizer V Studio 2 Pro, an update to its AI-powered vocal synthesis software. Version 2 of the software and all accompanying voices are now available for pre-order, with an official launch scheduled for 21 March 2025. Since its initial release, Synthesizer V has provided musicians with a tool for generating and refining vocal performances. The software enables users to input melodies, write lyrics, and select from a variety of AI-driven vocalists while customising expressive details. With this new version, Dreamtonics has introduced a series of enhancements designed to improve realism, workflow efficiency, and creative control. Enhanced Vocal Quality Increased Processing Speed Phoneme Timing Panel Refined Vocal Modes Expression Pad and AI Retakes Smart Pitch Controls Mouth Opening Parameter Korean Language Support Synthesizer V Studio 2 Pro utilises recordings of real singers, processed through AI models to generate expressive vocal performances. For this version, Dreamtonics has retrained its AI systems and refined the vocal modes of each voice, ensuring improved stylistic variation and a higher level of detail in articulation. The software, alongside all version 2 voices, upgrades, and bundles, is available for pre-order at a discounted price until 20 April 2025. Pre-ordered products will be available for download from 21 March 2025. For further details on pricing and pre-purchase options, visit the Dreamtonics website at https://www.dreamtonics.com.Dreamtonics Announces The Release of Synthesizer V Studio 2 Pro
Key Features of Synthesizer V Studio 2 Pro
Updated AI models allow for more natural human-like dynamics and articulation, improving the authenticity of synthesised vocal performances.
Rendering speed has been improved by up to 300% without requiring dedicated GPU hardware, enabling a smoother offline experience.
This new panel allows direct manipulation of phoneme intensity and timing within a note, providing detailed control over articulation and plosive onsets.
Users can now assign distinct vocal modes to pitch, timbre, and pronunciation, enhancing the flexibility of vocal characterisation.
The Notes panel now integrates an Expression Pad and a single-click AI Retakes feature, simplifying phoneme timing adjustments.
Pitch expressions can now be shaped more intuitively, offering greater precision in vocal phrasing.
A new control that influences vowel pronunciation, allowing users to accentuate words or modify phrase articulation for added depth.
All upgraded voices now include Korean as a cross-lingual synthesis option.Pre-Order and Availability
Follow Attack Magazine
Related