Version Change History
Separate vocals and instrumental tracks from audio or video in batches on your Mac. Local AI processing means no uploads, protecting your privacy.
V3.1
- Optimize separation model inference parameters for better results
- Fix several crash-causing issues
V3.0
- Upgrade to a more advanced model for separating vocals from background music
- Simplify the interface for a more intuitive user experience
V2.0
- Added the ability to segment a video or audio file based on VAD parameters. For example, you can automatically split a long conversation file into multiple segments according to the specified parameters, with shorter speech segments being automatically merged.
V1.0
Key feature is separate vocal and background music tracks from video or audio files. All operations are performed locally using AI Model, with no need to upload any files, ensuring personal privacy.
Features:
- Supports batch processing of video and audio files to enhance efficiency.
- Allows different filtering operations on audio or separated tracks, such as noise reduction and Fast Fourier Transform.
- For video files, it supports replacing the original audio track with the separated vocal or background music after separation.