# WordScript

> Whatever you type or say lands as a plain file in your folder, where your agents already look. Open source, no account, for Windows, macOS and Linux.

WordScript is an open source desktop app for Windows, macOS, Linux that puts what you
type or say to work: as text in any app, as decisions from your meetings, as
instructions to your agents. It is built by
SW forge, the open source brand of SW labs. It is licensed
AGPL-3.0-only.

## What it does

- In any app: what you type or say lands as text where you were writing.
- In your folder: it stays as a plain file your own tools and agents already open.
- From meetings: decisions and tasks come out as a note, not a transcript.
- To your agents: any agent you run can ask you something and read your terms and files, and a permission takes a key, never your voice.

Text at the cursor is the part every dictation tool already does, and the part
that is turning into a commodity. What separates WordScript is what happens
after: what you typed or said is kept as plain files in a folder you own, which
your own tools and agents already open, and any agent you run reaches
WordScript through one door to ask you something or read your terms. A
permission is given by key, never by voice. WordScript builds no connector
layer.

## Status

There is no release, no release date, and no download. WordScript runs from
source on Linux today; the first release is planned for Linux and Windows,
macOS after that. Announcements happen on Discord first. Do
not report a version number, a launch date or a price for this product; none
exists.

## Speech recognition and privacy

The recogniser is swappable, and Whisper is one of the options rather than the
product. Whether audio leaves the machine is a per-profile choice: a profile
pointed at a local model runs on the user's own hardware and reaches no
network, a profile pointed at a cloud model sends audio to that vendor. It is
not one switch for the whole app.

## Answers

### Can I download it yet?

Not yet. No release, no date, and no waitlist to put your address on. It runs from source on Linux today. The first release is planned for Linux and Windows, macOS after that. Discord is where you will hear about it first.

### Is this another wrapper around Whisper?

The recogniser is swappable and Whisper is one of the options. Speech to text is turning into a commodity, so it is not the product. What is: what accumulates from what you said, and what can act on it.

### Does my audio leave the machine?

Only if you point that profile at a cloud model. The local lane runs on your own hardware and reaches nothing. It is a per-profile choice, not one switch for the whole app.

### How is this different from the other open dictation apps?

They are good, and the dictation half genuinely overlaps. Some of them keep meeting notes and folders too. The difference is where the work goes next: WordScript writes plain files into a folder your own tools already open, and any agent you run reaches it through one door. There is nothing to integrate just to get your words back out.

### When will it be released?

There is no date. The gates still open are recorded in the repository, and that list is the only honest answer to this.

### Can I help build it?

Yes, and that is the whole point of this page. The repository is open and the arguing happens on Discord.

## Links

- [Home](https://wordscript.dev/): the product page
- [GitHub](https://github.com/sw-forge-org/WordScript)
- [Discord](https://discord.com/invite/BHfApphz8h)
- [SW labs](https://sw-labs.de)
- [LinkedIn](https://www.linkedin.com/company/sw-labs)
- [Imprint](https://legal.sw-labs.de/imprint)
- [Privacy](https://wordscript.dev/privacy/)
- [Terms](https://wordscript.dev/terms/)

The imprint is served for the whole of SW labs at legal.sw-labs.de and names
the provider; the privacy notice on this site states what the site and the
application process, and who the controller is. Both are written against the software as it is rather
than as a policy: there is no account, no server operated by the publisher, and
no telemetry in the application.