Skip to content
SPECIFICTION
Get listed

xinxin-song

github.com

WindowsSelf-hosted
Visit github.com
Spec score 6.5 #54 of 56 in AI song cover generators

Spec sheet

Purpose
xinxin-song is a local AI vocal-cover pipeline that takes an original song and a specified voice model to produce a cover.Read 11 Oct 2026 · github.com
Integrations
The documented pipeline uses Demucs, RVC, and ffmpeg, and accepts vocals prepared separately with UVR5.Read 11 Oct 2026 · github.com
License
The repository says its code is released under the MIT License.Read 11 Oct 2026 · github.com
Audio controls
The CLI supports pitch shifting, selectable F0 methods, RVC index tuning, denoising options, and WAV or MP3 output.Read 11 Oct 2026 · github.com
Dependencies
The setup instructions call for Python environments for the pipeline and RVC, FFmpeg, RVC models, and a trained voice model.Read 11 Oct 2026 · github.com
External audio
Users can provide externally separated vocals and accompaniment, allowing them to skip Demucs separation.Read 11 Oct 2026 · github.com
External vocals
Users can provide externally separated vocals to skip Demucs, with UVR5 given as an example tool for manual separation.Read 11 Oct 2026 · github.com
Hardware target
The development document names an RTX 5070 Ti with CUDA 12.8 and PyTorch cu128 as its hardware target.Read 11 Oct 2026 · github.com
Inference only
The V1 pipeline handles inference for one song; voice-model training is done separately with the RVC WebUI.Read 11 Oct 2026 · github.com
Mixing
The documented mixing stage uses FFmpeg loudness normalization and a limiter to help manage loudness and clipping.Read 11 Oct 2026 · github.com
Output files
By default, each song gets its own output directory containing intermediate audio, the final cover, a parameter snapshot, and a run log.Read 11 Oct 2026 · github.com
Processing
Its pipeline separates vocals and accompaniment with Demucs, converts the vocals with RVC, then mixes the converted vocals with the accompaniment.Read 11 Oct 2026 · github.com
Requirements
Setup requires two Python virtual environments, ffmpeg, RVC model assets, and a trained voice model; the documented RVC setup specifies Python 3.12 and CUDA 12.8.Read 11 Oct 2026 · github.com
Rights guidance
The README says cover distribution is subject to voice and copyright rights, advises getting authorization before public sharing, and warns against impersonation.Read 11 Oct 2026 · github.com
Scope limit
The documented V1 scope is inference for one song at a time; the development document says batch processing is not included in V1.Read 11 Oct 2026 · github.com
Security and privacy
The maker describes the pipeline as locally deployed and documents local output files and logs; the pages opened make no security certification or compliance claim.Read 11 Oct 2026 · github.com
Voice training
The project handles inference only; voice-model training is done separately using RVC’s WebUI.Read 11 Oct 2026 · github.com
Windows setup
The documented setup uses Windows commands, including `winget` for FFmpeg and Windows virtual-environment activation paths.Read 11 Oct 2026 · github.com

Where Specifiction places it

Alternatives to xinxin-songAll alternatives →