New OpenVINO AI results are now accessible to Windows users within the Audacity music software system. The latest features comprise Music Generation, Music Style Remix, Music Separation, Noise Suppression, and Transcription for podcasts.
Intel has introduced OpenVINO (Open Visual Inference and Neural network Optimization), a toolkit that empowers deep learning models to operate locally on Intel hardware. These innovative OpenVINO functionalities leverage AI integrated directly into your device.
Audacity elaborates on the functionality of each feature:
- Noise Suppression effectively reduces sound, akin to Audacity’s Sound Removal effect.
- Whisper facilitates sequencing, enabling transcription and translation of terms and outputs to a label track.
- Steady Diffusion is utilized in Songs Generation and Music Style Remix to craft new compositions.
- Music Separation divides songs into vocal and instrumental segments, including voice, drum, bass, and a combined section for other elements, ideal for creating playalongs and sheets.
To access these OpenVINO applications, visit Intel’s dedicated GitHub platform. While instructions are not provided, there may be an option to compile the program from source on Linux and macOS.
Audacity is a popular open-source audio editing tool within Linux communities, known for enhancing voice recordings. The integration of these AI tools on Linux systems may require individual compilation, with potential for community-driven accessibility and distribution.
