What we’re building
Every tool here is free, unlimited and runs on your own device — Your files are never uploaded — everything runs on your device. We build in the open; this is the honest state of things and the order we’re working in.
Live now
7 tools-
Transcribe audio & video
Turn any recording into text with timestamps and speaker labels.
Open -
PDF editor
Merge, split, reorder, rotate, delete and extract pages.
Open -
Remove background noise
Clean hum, hiss and room noise out of a voice recording.
Open -
Transparent background maker
Cut out the subject and download a transparent PNG.
Open -
Image to text (OCR)
Pull editable text out of a photo, screenshot or scan.
Open -
Upscale images
Enlarge a photo 4× and recover detail with AI, then download it.
Open -
PDF to Markdown
Convert a PDF into clean Markdown — headings, lists and tables — for notes or AI.
Open
Building next
In priority order — what we pick up as each one ships.
-
Text to speech
Natural-sounding voices, generated on your own machine.
-
Meeting notes
Turn a recording into a summary and action items — knows who spoke.
Exploring
Bigger bets we’re weighing — heavier to run in a browser, so they come once the ground is laid.
-
Split music into stems
Separate vocals, drums, bass and the rest from any track.
-
Private AI chat
A capable assistant that runs entirely on your device — nothing sent to a server.
Want a say in the order?
The engine is open source. Tell us what you’d use — or help build it — on GitHub.