Your words.Your pace.
A teleprompter that follows your voice. For your laptop’s webcam or a teleprompter rig: it waits while you ad‑lib, picks you up when you start again, and runs on your own computer.
Free and open source Not released yet A desktop app for macOS, Windows and Linux
An animation of Speaking Glass's stage following a voice: the words already spoken dim as the text moves to keep the next line beside two markers. When the speaker goes off script the text waits, and it carries on once they are back.
How it works
Write it. Present it. Read it.
No scroll speed to set and no operator to brief. Three steps, and the last one is just talking.
Write your script.
Write it in plain Markdown the way you’d say it, with a cue in square brackets for a note you see but never say.
Press Present.
It opens full screen on your prompter’s display, mirrored if the glass needs it, or in a window beside your webcam.
Read it aloud.
The line you’re on stays between the markers at whatever pace you speak, and waits while you ad-lib.
Features
Made for the way you read.
Write in Markdown, and read from mirrored glass or a window under your webcam, at a size set for the distance.
Built for glass.
Prompter glass reflects the screen beneath it, so Speaking Glass mirrors the script to read forwards. It recognises the Elgato Prompter and Prompter XL.
Scripts in Markdown.
Plain text with a few marks: square brackets add a pause, a new part or a cue you see but never say. Write GUI, say “gooey”.
Readable at a distance.
Text is sized for the distance you read from, not in pixels, so it looks the same size at a desk or across the room. Set in Atkinson Hyperlegible Next, with presets for desks, webcams and the Elgato rigs.
Takes and parts.
Start from the top, from the cursor or from any part. Practise rehearses without reporting anything, and every take ends with a short summary of how following went.
Your files, on your disk.
Every script is a plain Markdown file on your disk that any editor can open. Revision history keeps earlier versions to restore, and Export all data writes everything to one folder.
A closer look
From first draft to final take.
Real screens from the app, in the order you’ll meet them.
Library
Every script at a glance.
The library lists every script with its opening line and roughly how long it takes to read, so you can tell your drafts apart before you open one.
- A script with something to fix is marked Needs attention
- Import .md and .txt files, or drag them in
Editor
Write in Markdown, read it as a document.
Type a cue like
[Cue: look at the lens]in Edit, and Preview shows it as an amber pill: a note on the glass that voice following skips.- Edit, Preview, or Both side by side
- Find and replace, and autosave
Reading window
One screen is enough.
No rig and no second display. Put the Reading window just under your webcam and read from the laptop you record on, with the line you’re on between the two markers in the margins.
- Paper or Dark appearance
- Text size, line width and spacing to suit you
Take controls
When it isn’t sure, it asks.
If Speaking Glass can’t tell where you are, the text holds and the markers go hollow. The Take controls offer the nearby lines you might be on: pick one, or keep reading and it finds your place.
- Previous and Next sentence, or Set my place
- A for auto-scroll, with [ and ] for pace
Privacy
Your voice stays here.
Speech recognition and following run on your computer. Speaking Glass does not upload your microphone audio or your scripts.
No account or API key.
There is nothing to sign up for and no key to paste in.
No analytics client or crash reporter.
Logs are written on your computer and are not uploaded. Support bundles are created only when you ask for one, and go only where you send them.
One-time speech model download, about 128 MB.
Voice following needs it. It downloads only when you choose to install it, from the Welcome screen or Settings › Speech, and is checked against a SHA-256 checksum built into the app.
Update checks you can turn off.
Speaking Glass checks updates.speakingglass.com for a newer version shortly after it opens and every six hours. You can turn that off in Settings › Data, privacy & updates. An update installs only when you choose, never during a take.
Questions
Before you record.
Short answers on cost, rigs, privacy and installing.
Still have a question? Ask on GitHub
Yes. Speaking Glass is free and open source under the MIT licence, with no paid tier and no account to create. The code, the releases and the issue tracker are all on GitHub.
No. A laptop and its webcam are enough. Speaking Glass presents in one of two ways, and you can switch between them during a take:
- Reading window keeps the script in a window you can size and move, so it can sit just below your webcam.
- Teleprompter fills the display behind your rig’s glass, and can mirror the text for the beam splitter.
Yes, the Elgato Prompter and the Prompter XL both work. Choose the Prompter as your display in Settings › Prompter display and rigs. Speaking Glass recognises both and sizes the type for them automatically. Calibration is optional: it has a preset for each, to fit the type to how far you actually sit, and it offers to mirror the text for the glass.
Mirror the text in one place only. If Elgato Camera Hub already flips the Prompter’s picture, leave Speaking Glass’s Horizontal mirror off.
It holds. While you say something that isn’t in the script, the text stays where you left it, and it moves again once Speaking Glass finds your place. Start a sentence over and it follows you back. When it isn’t sure, it waits rather than guessing ahead: a deterministic engine, not a language model, decides where you are, on your own computer.
To move it yourself, pick your line in the Take controls or choose Set my place. If it keeps losing you, press A for auto-scroll. The docs list every take shortcut.
Only to download the speech model and to check for updates. Speech recognition and following run on your computer. Once the model is installed, you can write and present without a connection.
The speech model is downloaded when you choose to install it. It is about 128 MB, and you fetch it once. You can turn the update check off, and the network inventory lists every network path in the app.
No. Speaking Glass does not upload your microphone audio or your scripts. Speech recognition and following run on your computer. Your scripts are Markdown files on your own disk.
Support bundles are created only when you ask for one, and go only where you send them. The privacy policy has the detail.
Yes. The speech model Speaking Glass installs is an English one, so voice following works with English speech only.
Scripts in other languages still work. Press A for auto-scroll during a take, or move the script by hand.
Any microphone your computer sees: built in, USB or Bluetooth. The closer it sits to you, the less of the room it hears. Settings › Audio has a level meter and Test transcription, so you can check it before a take.
The installer isn’t code-signed yet, so Microsoft Defender SmartScreen stops it with a “Windows protected your PC” notice. Choose More info, then Run anyway.
To check the file first, run Get-FileHash on it in PowerShell and compare the
result with its line in SHA256SUMS-windows.txt on the release page.
Speaking Glass checks updates.speakingglass.com for a newer version shortly after it opens and every six hours, unless you turn that off, and installs one only when you choose to, never during a take.
When there is one, a notice in the corner of the window offers Install and Restart or Later. Installing restarts Speaking Glass, and your scripts and settings stay as they are. A Linux .deb can’t replace itself, so there the notice offers Download instead.
Updates are signed and verified. To stop the check, turn off Check for updates automatically in Settings › Data, privacy & updates.
Download
Free for macOS, Windows and Linux.
A desktop teleprompter, open source, with no account to create. The first release is on its way: follow it on GitHub to hear when it lands.
macOS
Signed and notarised .dmg
Requirements
- macOS 12 or later
- Apple Silicon or Intel
Not released for macOS yet
Windows
64-bit installer (.exe)
Requirements
- Windows 11
- Intel or AMD 64-bit (x86-64)
- Windows 10 should work, untested
Not released for Windows yet
Linux
AppImage, or a .deb package
Requirements
- Ubuntu 22.04 or newer
- Intel or AMD 64-bit (x86-64)
- WebKitGTK 4.1
Not released for Linux yet
On every platform
- A microphone and English speech, for voice following
- A second display, if you use a prompter rig
When it first opens
Start writing straight away. Voice following needs a one‑time English speech model, about 128 MB, from the Welcome screen. First run, step by step
Updates
Speaking Glass looks for a new version every six hours, unless you turn that off, and installs one only when you choose to. The .deb is the exception: its updates come from here. How updates work
Speak naturally.
Keep your place.
Free and open source, for macOS, Windows and Linux.