Skip to content
SPECIFICTION
Get listed

Nova-Vox vs SoulX-Singer

Nova-Vox

nova-vox.org

SoulX-Singer

github.com

Side by side

FigureNova-VoxSoulX-Singer
Price fromFreeFree
Free planYesYes
Free trial——
Open source——
Web—Yes
WindowsYes—
Linux—Yes
Self-hosted—Yes
Plans published11
Spec score · AI Singing Voice Generators7.4 (#18)8.2 (#10)

Plans

Nova-Vox

  • Nova-Vox 1.0Free

Nova-Vox pricing →

SoulX-Singer

  • SoulX-SingerFree

SoulX-Singer pricing →

In their own words

Nova-Vox

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.

Visit nova-vox.org

SoulX-Singer

SoulX-Singer is a singing voice synthesis model that generates voices for singers it has not been tuned on. Pitch, rhythm, and expression can be guided by melody-conditioned F0 contours or score-conditioned MIDI notes. Its voice-conversion system changes raw singing audio to a target singer’s voice while retaining melody, rhythm, and lyrics, without requiring lyric or MIDI transcriptions. It supports Mandarin Chinese, English, and Cantonese, plus singer-timbre cloning, cross-lingual synthesis, and lyric editing while retaining natural prosody. Preprocessing tools handle vocal separation, dereverberation, F0 extraction, voice activity detection, and lyric and note transcription. Users can edit MIDI metadata, including lyrics, phoneme alignment, pitches, and durations, before synthesis. Soul-AILab provides generation and conversion demos and a separate MIDI editor through Hugging Face Spaces; the repository also supports local inference. Code and model weights use the Apache 2.0 license. Maintainers caution that automatic preprocessing may misalign singing with lyrics and notes, so manual correction may be needed.

Visit github.com