NNSVS vs SoulX-Singer
NNSVS
github.comSoulX-Singer
github.comSide by side
| Figure | NNSVS | SoulX-Singer |
|---|---|---|
| Price from | — | Free |
| Free plan | — | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | — | Yes |
| Windows | Yes | — |
| macOS | Yes | — |
| Linux | Yes | Yes |
| Self-hosted | — | Yes |
| Plans published | 0 | 1 |
| Spec score · AI Singing Voice Generators | 7.3 (#20) | 8.2 (#10) |
| Languages | NNSVS has been used to create singing voice synthesis systems for multiple languages, with the documentation saying 8 or more as far as its author knows. | The system supports Mandarin Chinese, English, and Cantonese. |
| Notable limitation | The documentation says the post-filter is currently not recommended and neural-vocoder support is limited. | The maintainers warn that automatic preprocessing may misalign singing audio with lyrics and notes and recommend manual correction. |
| Purpose | NNSVS is a neural network based singing voice synthesis library designed for research. | SoulX-Singer is a high-fidelity zero-shot singing voice synthesis model for generating realistic voices for unseen singers. |
Plans
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.