Split vocals, remove noise — right in your browser.
Vocal remover and audio denoiser powered by RNNoise (WASM). Separate vocals from background music, or clean up noisy recordings — 100% on-device, zero uploads.
Studio-grade audio. Zero uploads.
RNNoise WASM running locally in your browser — no servers, no API keys, no limits.
100% private
Your audio never leaves your device. All processing happens locally via WebAssembly.
Vocal separation
Split any stereo track into vocals and accompaniment using center channel extraction. Perfect for karaoke or sampling.
Noise reduction
RNNoise removes background hiss, fan noise, and environmental sounds while preserving clear speech.
WAV export
Download processed audio as high-quality WAV files. Use vocals, instrumentals, or denoised tracks anywhere.
Three steps. Zero servers.
- 01
Upload audio
Drag & drop an audio file or browse. MP3, WAV, OGG, M4A, FLAC — any format your browser supports.
- 02
Process locally
Choose vocal separation or noise reduction. RNNoise runs in your browser via WebAssembly — no uploads.
- 03
Download results
Preview the processed audio, then download as WAV. Vocals, instrumentals, or clean voice — take what you need.
About Vocal Studio
A free browser-based audio studio for two common jobs: removing background noise from recordings, and separating vocals from music. It is built for podcasters cleaning up a room recording, creators making karaoke or a cappella tracks, students extracting a spoken line, and musicians experimenting with stems — all without uploading audio to a cloud editor.
How it works
Files are decoded locally with the Web Audio API. The denoise path applies RNNoise-based suppression, a recurrent network trained to distinguish speech from background noise and running in real time via WASM. The separation path uses stereo phase and channel analysis to isolate centered vocals from accompaniment, exporting vocals and instrumental stems as separate WAV files. Everything runs in your tab — no upload, no job queue.
Limits & requirements
Stem separation works on stereo tracks (mono recordings cannot be split by channel positioning); vocal isolation is most effective for modern, center-mixed material. Denoising handles steady background noise well; sudden interferences like overlapping speech are harder. Long files scale with device memory.
Privacy
Recordings — rough takes, unreleased tracks, confidential sessions — never leave your machine. Processing is local with no server round-trip, no watermark, and no length-based paywall.