CleanTake
Patch a ruined line of speech with the same moment from your other recorder
Emerged finds new products worth a look, daily — what’s new today
AudioDrop
Split songs into stems and convert audio on your own machine, free, no upload
Musicians and editors can pull vocals, drums and bass out of a track without sending it to anyone's server or paying per minute.
AudioDrop is a set of free audio tools that run entirely in the browser. Its stem splitter separates a song into vocals, drums, bass and other using HTDemucs on WebGPU, with a fast preview pass first; a four-minute track takes about 20 seconds on an M-series Mac. It also converts formats, changes speed and pitch, adds effects and detects BPM and key. No account, watermark or limits; the 166 MB model downloads once.
More like this
Drop
Disposable, isolated homes for untrusted programs and coding agents on Linux
FireRedAudio
One open 9B audio model for speech recognition, understanding, TTS and editing
Tonefold
Open-source music sketchpad: AI writes parts into a piano roll you can edit
Pinch Sidecar
Live speech translation for any Chrome tab or video meeting, in the browser
Rescript
Edit podcasts and video by editing the transcript, entirely on your device