Audio tools

Audio transcription with Whisper. Drop in a recording and get editable text, plus SRT and WebVTT carrying timestamps, from any of four model sizes.

A vocal remover that splits a song into two stereo tracks, the voice on one and the instrumental on the other, using Deezer's Spleeter model.

A batch audio converter: load MP3, WAV, M4A, OGG or FLAC in any mix, queue as many as you like, and write M4A, WAV, Opus or FLAC back out with a zip at the end.

An audio cutter that keeps every part you mark and throws away whatever falls between them, fades and crossfades included.

An audio joiner for stitching clips into one track: queue them in order, set a crossfade if you want them to blend, then export M4A, WAV, Opus, or FLAC.

Normalize audio by its loudest peak: see the lift in decibels before you press, pick a headroom preset, and download a copy that lands on the target.

Reverse audio end to end and hear it play backwards, then save the flipped clip as M4A, Opus, WAV, or FLAC. Sample rate and pitch stay exactly where they were.

Change audio speed anywhere from 0.5x to 2x: drop a track to 0.75x for a slowed edit, or lift it to 1.5x for nightcore. Pitch follows the speed. Exports as M4A, WAV, Opus or FLAC.

An audio visualizer that splits whatever's playing into 1,024 frequency bands and draws each one as a bar, updated every frame.

BPM counter with two ways to get an answer: analyze an audio file, or tap the beat out yourself. File detection always lands between 90 and 180 BPM.

Edit an MP3's ID3 tags and cover art: title, artist, album, genre, year and the picture, with every other frame carried through. Fix Unknown Artist.

Stereo to mono, or mono to stereo: pick a direction and get the file back as M4A, Opus, WAV, or FLAC.

Remove background noise from audio with DeepFilterNet, a speech model that runs on your device. Hum, fans and hiss drop away, the voice stays, and the clean take saves as M4A, WAV, Opus or FLAC.

Remove silence from audio automatically. Two numbers decide what goes: how quiet a gap has to be, and how long it has to last.

Text to speech two ways: the voices your device already has, or a 13-voice English model that hands you a file.

A tone generator that sounds the moment you press Play: type or slide to any frequency, sweep 20 Hz to 20 kHz, or play white, pink and brown noise.

A voice recorder with a real pause: hold the take, breathe, carry on into the same file. Live input meter, a mic picker when you have more than one, and M4A, WAV, Opus or FLAC out.