Getting started

ThoughtSift turns a spoken thought into a visual artefact — a hand-drawn diagram you can look at, share, and act on.

The three stages

Every capture moves through the same pipeline:

1. Capture & transcribe — record your voice (or type), and ThoughtSift produces a transcript.
2. Sift intelligence — the text transcript is shaped into clean threads, and a diagram style is recommended.
3. Visual generation — a diagram is generated and persisted to your local history, ready to share.

Your first capture

1. Start a recording from the Action Button, a widget, or the app.
2. Speak your thought. The screen can lock while recording continues.
3. ThoughtSift transcribes, sifts, and generates a diagram you can review on the result screen.
4. From there you can share a link or replay it later from history.

Read How it works for the full pipeline, or jump to Capture.