demucs

Open-source AI video localization and dubbing for YouTube/Bilibili: speech recognition, subtitle translation, voice cloning, audio mixing and rendering. 开源 AI 视频翻译配音工具。

Self-hostable web app for isolating the vocal, accompaniment, bass, and drums of any song. Supports Spleeter, Demucs, BS-RoFormer. Started in 2019.

A Streamilt web app for music source separation & karaoke

🎛 Stemgen is a Stem file generator. Convert any track into a Stem and have fun with Traktor.

A local GUI music source separation tool built on Tkinter and demucs serving as a free and open source Stem Player

(Windows/Linux/MacOS) Local WebUI with neural network models (Text, Image, Video, 3D, Audio) on python (Gradio interface). Translated on 3 languages

Production-ready UVR5 CLI & Docker image. Run SOTA separation models (Roformer, SCNet, MDX, Demucs, VR Architecture) on headless GPU servers without dependency hell.

C++ ONNX/ORT inference for Demucs

Implements ML audio separation algorithm on audio from YouTube or Spotify resulting in "stems" for download (e.g. vocals, drums, bass) in MP3, WAV or FLAC.

Split any song into stems — vocals, drums, bass, and more. Fast music source separation for Apple Silicon, powered by MLX.

A simple and efficient self-hosted application to separate vocals from music using Artificial Intelligence.

We implemented the DEMUCS model for speech enhancement in the time-frequency domain, and additionally implemented HD-DEMUCS.

Modern source separation

Create and explore isolated tracks from music files

100% local video dubbing on your desktop — dub videos in your own voice. Private AI dubbing with no cloud, no uploads, no time-stretching.

Music -- separate into stems, modify, convert to midi, add synth sounds, remix.

Python DJ engine that renders beat-locked, key-aware transitions between any two tracks. Demucs stem separation, dynamic EQ fade, procedural bridge beats, ITU-R LUFS mastering. FastAPI + Streamlit.

all-in-one ai-midi-pipeline

Add captions to any video or song, in any language — 100% on your device, no cloud. Hinglish-first. Free, open-source, and works with any AI agent.

Gerador local de karaoke UltraStar por forced alignment: a partir da letra que voce ja tem, sincroniza ao audio (WhisperX + Demucs), extrai pitch/BPM e monta o pacote jogavel. Tauri + Rust + Python. Windows, bilingue PT/EN.