Anjok07/ultimatevocalremovergui

GUI for a Vocal Remover that uses Deep Neural Networks.

What it solves

Ultimate Vocal Remover (UVR) is designed to isolate and remove vocals from audio files. It provides a user-friendly interface for applying advanced AI models to separate music tracks into distinct components, such as vocals and instrumental backing.

How it works

The application runs state-of-the-art source separation AI models locally on your computer. It bundles the necessary software, including Python and PyTorch, to handle the heavy computational lifting required to process audio. Users can select different models to perform the separation, and the tool supports additional features like time-stretching and pitch-shifting using the Rubber Band library.

Who it’s for

UVR is for users who need high-quality audio source separation for music production, remixing, or editing. It is suitable for those comfortable with installing desktop software on Windows, macOS, or Linux, and who have hardware capable of running intensive AI tasks (Nvidia GPUs are recommended for best performance).

Highlights

  • Uses custom-trained, state-of-the-art AI models for high-quality vocal removal.
  • Includes a graphical interface that simplifies complex AI-driven audio processing.
  • Supports advanced audio manipulation tools like time-stretching and pitch-shifting.
  • Provides cross-platform support for Windows, macOS, and Linux.
  • Completely open-source and free to use under the MIT license.

Related

  • Project
    m-bain/whisperX

    WhisperX is a Python library that speeds up OpenAI’s Whisper transcription by batching, adds per‑word timestamps via forced alignment with wav2vec‑2.0, and can label speakers using pyannote‑audio. It runs on GPU (or CPU), supports several languages, and is installable via pip.

  • Project
    index-tts/index-tts

    IndexTTS is an open‑source zero‑shot multilingual text‑to‑speech system that can clone a voice from a single reference audio. The latest version (2.5) supports Chinese, English, Japanese, Spanish, and Arabic, and provides fine‑grained control over emotion, speaking speed, and pronunciation (Pinyin/CMU phonemes/Japanese Kana). It runs fast with half‑precision (BF16/FP16) inference, optional DeepSpeed acceleration, and can be served at scale via a vLLM recipe. The repo includes pretrained checkpoints, a web UI, and a Python API, and is released under Apache‑2.0.

  • Project
    resemble-ai/chatterbox

    A family of open-source text-to-speech models providing low-latency voice cloning and multilingual speech generation across various model sizes for GPU and CPU deployment.

  • Project
    Zackriya-Solutions/meetily

    A privacy-first AI meeting assistant that captures, transcribes, and summarizes meetings locally on your own infrastructure to ensure data sovereignty.