Onwords FAQs

About Onwords #

What is Onwords? #

Onwords is a teleprompter for Windows that follows your voice. You paste in a script, and as you read it aloud the app tracks where you are and scrolls the text to keep your current line centred on screen.

How is it different from a normal teleprompter? #

A normal teleprompter scrolls at a fixed speed, so you have to match your delivery to the machine. Onwords does the opposite — it listens to you and moves the text to match your pace. Pause for emphasis and it waits. Speed up and it keeps up.

Is there a Mac version? #

Coming soon. Get in touch at https://chaoscreated.com/get-in-touch-with-us/ if you would like to hear when it lands.

Do I need a special teleprompter rig? #

No. Onwords works on any screen. If you do use beam-splitter teleprompter hardware, there’s a mirror mode that flips the text horizontally for the glass.

What does it cost? #

£19.99 (about $23.99), once. Most of the apps we tried wanted more than £10 a month, forever. Onwords costs less than two months of that, and then it’s yours.

There is a free 7-day trial on the Microsoft Store, with everything unlocked.

Do I have to buy it again for a new PC? #

No. A Microsoft Store purchase is tied to your Microsoft account, not to the machine. Sign in to the Store on your new PC and install Onwords from your library; it arrives already licensed. Microsoft’s current rules allow an app on up to ten of your Windows devices at once.

Your script does not travel with the licence — it is saved only on the computer you wrote it on — so copy it across if you need it.

Getting started #

How do I use it? #

1. Paste your script into the box and click Start Prompting. 2. Choose your microphone from the Mic dropdown. 3. Click Start Listening and begin reading.

That’s Voice-Follow, the default. If you’d rather have a steady scroll, switch to Auto-Scroll in the toolbar: the microphone controls give way to a Play button and a Speed slider in words per minute.

The line you’re reading is highlighted and sits on the guide line across the middle of the screen, with the lines above and below faded back. A marker sits under the word the app has reached.

What do I need to run it? #

Windows 10 version 1809 or later, or Windows 11, on a 64-bit machine (Intel, AMD or ARM) — plus a microphone. Nothing else: no account, no subscription key, no internet connection, and no runtimes to install first. The speech engines are included, which is why the app is around 400 MB installed.

One feature needs more: the script rewrite (the wand beside the script box) uses the AI hardware in a Copilot+ PC and stays hidden on other machines.

Where do I find the introduction again? #

The first time you run Onwords, a short “Getting started” pane explains how it works. It does not appear again after that, but Help > Getting Started opens it whenever you want it.

Release notes work the same way: after an update, the megaphone in the top-right corner opens by itself to show what changed. Click it any time to read them again, or use Help > What’s New.

Is my script saved? #

Yes. Your script is saved on your computer automatically and restored the next time you open Onwords. You don’t need to paste it again between takes or sessions.

Can I open a script from a file? #

Not currently — scripts are pasted in. [Remove this entry if you’d rather not draw attention to it.]

How long can a script be? #

Long enough that it isn’t worth worrying about. The editor shows word count, character count and an estimated reading time as you type, and flags anything beyond about 5,000 words — roughly forty minutes of continuous speech — as unusually long for one sitting. That’s guidance, not a limit.

How the tracking works #

How does it know where I am in the script? #

The app listens through your microphone, converts your speech to text with a speech recogniser built into the app, and matches what it hears against your script. It looks at the last several words you’ve said and finds the place that best explains them.

The recogniser is a modern neural model that runs on your own processor. It was trained on real-world speech — podcasts and video as well as audiobooks — which is what lets it cope with accents and with a presenter standing well back from the microphone. The classic Windows recogniser is still there under View › Recognition Engine if you prefer it.

What if I stumble, or say something that isn’t in the script? #

Nothing breaks. The app needs only a few recognisable words to keep its place, so a fluffed line, a filler word or a short unscripted aside won’t throw it off. When it isn’t confident, it holds position rather than guessing.

What if I skip a section? #

It will catch up. When what you’re saying stops matching the area it’s watching, the app searches your whole script and jumps to where you’ve moved to. This usually takes a sentence or two.

The highlight lags slightly behind me. Is that a bug? #

No — that’s deliberate. The app waits until it’s reasonably confident before it moves, rather than leaping ahead on a single word it might have misheard. In practice the marker sits a word or two behind your voice, which is what keeps it steady enough to read from. The highlighted line is what you follow; the marker is a finer cue.

The “Heard” bar shows the wrong words. Does that matter? #

Usually not. That bar shows the recogniser’s raw output, and even a good recogniser mangles the odd name or technical term. Tracking doesn’t need a perfect transcript — only enough recognisable words to locate you in the script. If the transcript looks rough but the highlight is following you correctly, everything is working as intended.

The pill at the right of the bar names the engine that’s listening.

Can I improve recognition accuracy? #

Yes, several things help:

• Use a decent microphone positioned close to you, rather than a laptop or webcam mic. A wireless lavalier is the single biggest improvement for a presenter who moves about.
• Record somewhere reasonably quiet.
• Speak at a natural, even pace rather than rushing.
• Try the other engines under View › Recognition Engine. The default is tuned for general speech; the second neural engine is biased toward the words in your script, which can help with unusual names. The classic Windows engine is there too, and if you use it, training a Windows speech profile (Settings → Time & Language → Speech) tunes it to your voice.

Onwords already boosts a quiet microphone automatically, so distance from the laptop matters far less than it used to.

Which languages does it support? #

English. The built-in speech engines are English, and that is what we support.

If you present in another language you can try View › Recognition Engine › Windows (classic), which uses whichever speech recogniser Windows has installed for your current language — French and German ship with Windows, and others can be added through Settings → Time & Language → Language & region. We have not tested those and cannot promise how well they track.

Privacy #

Is my script sent anywhere? #

No. Your script stays on your own machine.

Where does the speech recognition happen? #

Entirely on your computer. The recogniser is bundled inside the app and runs on your processor; nothing is uploaded, no online service is involved, and no audio leaves your machine. The optional script rewrite also runs on the device.

Does it work without an internet connection? #

Yes, completely. Onwords needs no connection at any point.

Where can I read the privacy policy? #

At https://chaoscreated.com/docs/onwords-privacy-policy/, and from inside the app under Help › Privacy Policy.

Is my audio recorded or stored? #

No. Audio is processed as it arrives and is never written to disk. The only exception is one you switch on yourself: Help › Recognition Logging writes the recognised text (not audio) to a local file to help with support, and is off unless you turn it on.

Do I need an account? #

No. There’s no sign-in, and no account to create.

Presenting #

Can I use it with a beam-splitter teleprompter? #

Yes. Click Mirror to flip the text horizontally for the glass.

Can I make the text bigger or smaller? #

Use the A- and A+ buttons to suit your distance from the screen.

Can I run it full screen on a second monitor? #

Yes — drag the window to your second display and click Fullscreen, or use View → Toggle Full Screen.

Can I use it as a normal teleprompter, without voice tracking? #

Yes. In the prompter, switch the mode from Voice-Follow to Auto-Scroll. The microphone controls are replaced by a Play/Pause button and a Speed slider, so the script sits still until you press Play and you can set the pace in words per minute. Restart takes you back to the top and pauses, ready for a cue.

Can Onwords rewrite my script for me? #

On a Copilot+ PC, yes. A small wand button appears beside the script box. Pick a style — Neutral, Casual, Concise, Formal, or your own instruction such as “rewrite as a warm, upbeat voiceover” — and Onwords shows you the result before changing anything. Nothing is replaced until you say so.

This runs entirely on your device using the language model built into Windows. Your script is not uploaded anywhere, and it works the same as the rest of Onwords: offline.

The button is hidden on PCs without the hardware for it, and in two-speaker mode, where a rewrite would strip the “A:” and “B:” labels your script depends on.

Note that the rewriter shortens as it works — expect roughly 15% fewer words — so read the preview before replacing your script.

Support asked me for a recognition log. Where is it? #

Turn on Help → Recognition Logging. From then on, each listening session writes what the engine heard and where the marker moved to a plain text file:

%LOCALAPPDATA%\Onwords\recognition-log.txt

Help → Open Log Folder takes you straight there, and shows how much is on disk. It grows by roughly 30 KB per minute of speech, is capped at 5 MB (the oldest sessions roll into a .previous file), and is off by default because it contains what was said — the one thing Onwords otherwise never keeps. Switch it off again the same way when you’re done.

How do I start again from the top? #

Click ↻ Restart. This returns to the beginning of your script and clears the live transcript.

Can I correct its position manually? #

Yes. Use the up and down arrow keys to move the highlight a line at a time. You can also scroll with the mouse wheel at any point.

Can two people share a script? #

Yes. Tick Two speakers under the script box, select the lines belonging to one presenter, and click Speaker A or Speaker B. In the prompter, each speaker’s lines are tinted — pale yellow for A, pale blue for B — so you can see at a glance whose line is coming next.

Assignments are stored in the script itself as a short prefix (A: / B:), so they survive editing, they’re saved with your script, and you can type them yourself instead of using the buttons if you prefer. The labels are shown in the prompter but are never treated as words to be spoken — Onwords won’t sit waiting to hear you say “A”.

Both presenters need to be on the same microphone. Onwords follows whoever is speaking, so it tracks straight through the handovers; but if the second person is off-mic or across the room, it won’t hear their lines and the highlight will sit still until someone it can hear resumes.

Troubleshooting #

Nothing happens when I speak — the highlight doesn’t move at all. #

This is nearly always the microphone selection. Windows’ default recording device is often not the microphone you’re actually speaking into — it might be a webcam, a virtual audio device, or a built-in array pointed at the wrong thing, and the signal from it can be far too quiet for speech recognition to work with.

Open the Mic dropdown and pick your actual microphone by name, then click Start Listening again. If the “Heard” bar starts showing words, it’s working.

Onwords will usually tell you when this is the problem. While it’s listening, a small level meter sits next to the Mic dropdown — it should move as you speak. If nothing usable arrives for a few seconds, an orange bar appears across the top of the script saying No audio detected. That message means the microphone, not the tracking.

The app isn’t hearing me at all. #

If the No audio detected bar is showing, work through these in order:

1. Check the Mic dropdown is set to the microphone you’re actually speaking into, not “System default” 2. Check Windows can hear that microphone: Settings → System → Sound → Input, and watch the input level as you speak 3. Confirm Windows lets desktop apps use your microphone:

Settings → Privacy & security → Microphone #

4. Click Stop Listening, then Start Listening again

The highlight jumped to the wrong part of my script. #

Scripts that repeat a phrase in several places can occasionally cause this. Use the arrow keys to move the highlight back to the right line, or click ↻ Restart and carry on from the top. Continuing to read will normally also bring it back on its own.

Can I change microphone while I’m recording? #

Stop listening first, choose the new device, then start listening again. The dropdown is locked while the app is listening, and so is the recognition engine menu — changing either mid-take would restart recognition under you.

Windows warned me about the app when I installed it. #

[If the build is still unsigned at launch, explain here that Onwords isn’t yet code signed, so SmartScreen shows a warning, and how to proceed past it. Remove this entry once signing is in place.]

I’ve found a bug, or something isn’t covered here. #

Get in touch at https://chaoscreated.com/get-in-touch-with-us/ — and if it is about voice tracking, a recognition log (see above) will help us see what happened.