Open Source
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace.
Ultimate Vocal Remover GUI (UVR) is a deep-learning-based desktop tool for separating vocals, instrumentals, and individual stems from any audio track. It bundles multiple state-of-the-art source separation models (MDX-Net, VR Architecture, Demucs) behind a single PyTorch-powered interface. UVR is widely used by producers, remixers, and karaoke creators because of its high-quality stem isolation and offline operation.
myshell-ai
Instant voice cloning framework by MIT and MyShell with 36k+ GitHub stars, enabling zero-shot cross-lingual voice replication from just seconds of reference audio.
FunAudioLLM
Multilingual LLM-based TTS with zero-shot voice cloning, 9 languages, and 150ms streaming latency.
OpenBMB
OpenBMB's 2B-parameter tokenizer-free TTS model with 48 kHz output, 30-language support, voice cloning, and an Apache-2.0 license.
Alibaba Cloud Qwen Team
Open-source TTS series from Alibaba's Qwen team with 97ms streaming latency, 10-language support, 3-second voice cloning, and natural-language voice design. Apache-2.0 licensed.