1941 · CBS listening post
Your words,
put to work.
Whatever you type or say lands as a plain file in your folder, where your agents already look.
- Claude Code
- Neovim
- Codex
- Obsidian
- Gemini CLI
- Sublime Text
- Cursor
- IntelliJ IDEA
- GitHub Copilot
- Logseq
- Windsurf
- Emacs
- Zed
Each of these already reads a folder. None of them needed a plugin.
Words have always been put to work.
Someone had to carry them.
Where your words go.
Text at the cursor is the part every dictation app already does, and soon all of them will do it for free. This is what happens after.
Context. A dictation, a meeting, an uploaded file and a pasted link are the same kind of record, and they accumulate in a directory you own.
- You hold Ctrl+Space and talk into a new note
- One Markdown file lands in the folder
- Plain text, in the app you already use
Opens the meeting window: your microphone, the system audio, and the note filling in while people talk. It never inserts anything anywhere.
WordScript resolves the media stream. Nothing is kept but the audio it needs and the transcript it produces.
Notes after the call
Maria wants the migration held until the backfill lands.
Tuesday is the fallback, and she can move the review.
Open: who tells the support team, and when.
The agent. Any agent you run reaches WordScript through one door. A question is answered out loud. A permission takes a key, because a misheard word must not be able to approve anything.
- Your agent reads the file WordScript wrote
- WordScript asks, you answer out loud
- A permission takes a key, never your voice
The backfill will not finish tonight. Ship the migration behind the flag, or hold it?
Constructed example. Three intakes, one directory, and it is yours.
What you get.
- Profiles
A profile that changes the output.
Vocabulary, style, delivery and model belong to whatever you are working on. A commit message and a mail to a client are not the same job.
- The record
It shows what it changed.
Raw and delivered are stored apart. Every rule that fired is named, and audio it could not hear is marked as a gap instead of guessed at.
- Credentials
Your keys, your machine.
API keys live in the operating system secret store, and the config file is scrubbed on save. Nothing leaves for anywhere you did not pick.
- Sources
Bring audio in.
An uploaded file, or a pasted video, podcast or direct audio link, becomes the same kind of record as something you said out loud.
- Licence
AGPL-3.0, the whole thing.
No open core with the good half behind a login. Read it before you decide anything.
Nothing runs on one engine.
A profile decides what handles each job, and the jobs do not have to agree. Cleanup on a small local model, the agent on a frontier one, dictation wherever it is fastest that week. Four lanes, and you pick by what it costs you to run rather than by whichever model is fashionable this month.
- Dictationwhat you said, into textCloudwhisper-large-v3-turbothe fastest lane, and you are waiting on this one
- Cleanuprepairs what you saidLocalllama-3.2-3b-instructa repair job a small model does well, and it never leaves the machine
- Translatesays it in another languageYour servertyped on the endpointthe box in the next room, already running
- The agentanswers, and can actCloudclaude-sonnet-5the one job worth a frontier model
With the network off, it is the same app.
The Local lane is the whole product, not a degraded one: dictation, cleanup, rewrite, translate, the agent. Weights on your disk, a runner on 127.0.0.1, no account and no key.
- No keynothing to sign up for, nothing to revoke
- No requestno bytes leave the machine, so nothing can be logged
- 148 MB
- if you only dictate: one speech model, and that is a working install
- 7.3 GB
- if you run all eight jobs locally: 4 files, fetched once
4 lanes and 35 models across 7 vendors, in the catalogue both runtimes read. Every model in the profile is that file's own default for that job. Last checked 2026-08-17.
The honest 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.
Nothing is released yet.
That is the point.
I never wanted a better ear. They all have an ear. What I kept missing is what happens after it: my words stay mine, in folders I own, and exactly one agent gets to touch them. It should be the best dictation app on the desk too. Give me a year.
Or write to