| Key features | - Separate audio into three stems: Vocal, Background Music, and Other
- Download individual stems or all stems together
- Process audio and video files up to 3 hours
- Support for 20+ audio and video formats
- Custom Mix to rebalance separated stems
- Process files up to 10GB in size
| - 15 playable virtual instruments including piano, guitar, drums, violin, cello, saxophone, trumpet, flute, clarinet, ukulele, harmonica, harp, kalimba, xylophone, and bass guitar
- AI voice cloning with 10-second voice sample recording for Chinese and English
- Speech-to-text transcription with support for 90+ languages and SRT subtitle export
- Stem splitter separating songs into vocals, drums, bass and other stems using Demucs model
- AI noise removal using deep neural network to clean audio from hiss, hum, wind and background noise
- Audio format conversion supporting MP3, WAV, M4A and WebM
- Audio effects including reverb, 8D audio, distortion, delay, echo, chorus, flanger, fade in/out and equalizer
- Signal generators for binaural beats, white noise, tone generation and metronome
- Audio editing with trimming, cutting, merging, reversing, normalization and compression
- Text-to-speech with 30+ AI voices in American and British English
|
|---|
| What makes it different | - Preserves dialogue quality while removing background music
- No installation required; runs entirely in browser
| - All processing happens entirely in your browser with no server uploads and no registration required
- Complete audio workflow from raw recording to finished export with 67 free tools
- Fully translated into 14 languages with every interface element localized
- All AI tools run entirely on-device with no server cost, no upload queues, and unlimited use
- Instant access to tools with no downloads, plugins or installation required
|
|---|
Music Remover
Soundtool