SoulX-Singer vs VoiSona Song
SoulX-Singer
github.comVoiSona Song
voisona.comSide by side
| Figure | SoulX-Singer | VoiSona Song |
|---|---|---|
| Price from | Free | ¥550/mo |
| Free plan | Yes | Yes |
| Free trial | — | Yes |
| Open source | — | — |
| Web | Yes | — |
| Windows | — | Yes |
| macOS | — | Yes |
| Linux | Yes | — |
| iOS | — | Yes |
| Self-hosted | Yes | — |
| Plans published | 1 | 7 |
| Spec score · AI Singing Voice Generators | 8.2 (#10) | 8.4 (#9) |
| Purpose | SoulX-Singer is a high-fidelity zero-shot singing voice synthesis model for generating realistic voices for unseen singers. | VoiSona is AI voice synthesis software that realistically reproduces human singing. |
| Support | The project lists three contact emails and invites technical discussion through WeChat or Soul app groups. | The maker directs software support requests through its inquiry form and lists support hours as 10:00 AM to 5:00 PM, excluding weekends and public holidays. |
Plans
VoiSona Song
- Chis-A voice libraryFree
- Free Chis-A voice libraryFree
- VoiSona editorFree
- Voice library monthly plan¥880 a month
- Voice library annual plan¥6,600 a year
- Voice library outright plan¥13,200, paid once
- Paid song voice librariesPrice not published
In their own words
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.
VoiSona Song
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.