Audio Eraser

Why It Exists

Users need to clean up or enhance audio in videos without professional editing software or multiple apps.

How It Works

Galaxy Audio Eraser is Samsung's AI-powered audio editing tool that can separate and modify specific sound sources within a video. Using on-device NPU processing and Samsung Cloud, the system identifies speech, background music, ambient noise, and sound effects. Users can remove unwanted sounds, enhance speech clarity, isolate a specific speaker, or replace background audio entirely.

Everyday Use Cases

• Background noise removal
• Speech enhancement
• Music isolation
• Sound effect extraction
• Audio replacement
• Dialogue isolation

User Workflow

• User opens a video in the Gallery app
• Audio Eraser analyzes the full audio track
• AI identifies and separates sound sources
• User selects which audio to keep, enhance, or remove
• Changes are applied and video is exported

AI Processing Flow

The audio track is processed by on-device NPU neural models for sound source separation. The system uses multi-channel audio analysis to identify speech, music, and ambient noise. Complex separation tasks are offloaded to Samsung Cloud with encryption. Speech enhancement uses voice isolation models. All processing preserves video sync and supports 4K export.

Inputs / Outputs

Inputs:

• Video file
• Audio track
• Sound source identification
• User selection of audio to keep or remove

Outputs:

• Separated audio tracks
• Cleaned audio mix
• Enhanced speech
• Replaced background audio
• Exported video with processed audio

Known Limitations

• Audio quality degrades with aggressive noise removal
• Limited to common sound types
• Requires sufficient audio contrast between sources
• Export adds processing time

Unsupported Scenarios

• Real-time streaming audio enhancement
• Live streaming noise reduction
• Multi-speaker conference calls
• Non-Samsung video files

Performance Notes

Sound separation in 3-5 seconds for 2-minute video; Speech enhancement in under 1 second; NPU acceleration reduces CPU load by 70 percent; 4K export takes 2-3x original video length

Available On

Shows where this feature is available and how its AI processing works on each platform. Availability may vary by device.

Research Status

Confidence and verification reflect how complete documentation is. Fields may show Not assessed or Not yet verified while research is ongoing - this flags gaps, not product deficiencies.

Research Notes

Available on Galaxy S24 series and newer; Requires One UI 6.1+; Supports MP4 and other common formats; Introduced with Galaxy AI in 2024

Details

Capability Mapping

This feature maps to canonical capability family: Image Generation.

Canonical capability: Image Generation.

• Image Generation - Creates novel imagery or emoji-like generated outputs from prompts.

Grounded in 3 device(s) on Galaxy AI.