Nova-Vox vs VoiSona Song

Nova-Vox is a free, open-source vocal synthesizer for Windows combining traditional and AI-driven methods. Its ESPER framework supports concatenative and granular synthesis and provides a foundation for AI systems. Voicebanks can package expressions, pitches, custom AI models and settings in one file. The engine chooses a suitable pitch for each note, while expressions can be entered with a single letter. A universal phonetics system is described as supporting any language, and a node editor builds adaptive post-processing effects. The Nova-Vox 1.0 download includes the Development Kit and AI base models for creating Voicebanks, delivered through a Windows setup executable. Commercial use is allowed. The maker identifies Johannes Klatt as maintainer and lead developer. The maker also reports performance issues, a prohibitively large installation and code issues in version 1.0. Mirai, the planned 2.0 release, has no release date.

VoiSona Song is AI voice synthesis software that reproduces human singing. It is available on iOS, macOS, and Windows, with a free editor and the Chis-A voice library available at no cost. Users can create vocals by entering notes and lyrics in a piano roll, importing MIDI into a DAW, or uploading MusicXML files. Editing controls cover phoneme timing, pitch, volume, vibrato, voice quality, and huskiness. On PC, the app can run on its own or as a VSTi or Audio Units plug-in. The iOS/iPadOS app runs standalone or as an AUv3 plug-in compatible with GarageBand, Logic Pro, Cubasis, and more. Export formats include WAV, MIDI, MusicXML, CCS, CCST, tsmsln, tssprj, and Lab; commercial use is allowed. Before a voice library is purchased, the free editor can make voices sing only the first 10 seconds of a song. Paid song voice libraries offer monthly, annual, and outright purchase options, with prices varying by library and displayed in yen. Sign-up is required, and an internet connection is needed for installation and some features. CeVIO Creative Studio and CeVIO AI exclusive voice libraries cannot currently be used.