intel/openvino-plugins-ai-audacity
A set of AI-enabled effects, generators, and analyzers for Audacity®.
What it solves
This project provides a set of AI-powered audio editing tools for Audacity, allowing users to perform complex audio processing tasks locally on their own hardware without needing an internet connection.
How it works
It integrates OpenVINO to run AI models on a computer's CPU, GPU, or NPU. It ports various specialized models—such as Meta's MusicGen and Demucs—from Python/PyTorch to C++ to enable high-performance local execution within the Audacity interface.
Who it’s for
Audio engineers, podcasters, and musicians who want professional AI audio tools like stem separation and noise suppression integrated directly into their digital audio workstation (DAW).
Highlights
- Music Separation: Splits tracks into drums, bass, vocals, and other instruments.
- Noise Suppression: Removes background noise from audio samples.
- Music Generation: Uses MusicGen LLM to create new music snippets or continue existing ones.
- Whisper Transcription: Generates label tracks for spoken audio or vocals using whisper.cpp.
- Super Resolution: Upscales audio for improved clarity and detail.
Related
- Project
- Project
- Project
- Project
- Project