Your phone is the remote
Scan a code once and your phone becomes a trackpad, a slide pad for the caret, the keys each mode needs and a big Talk button. It connects straight to your computer over your Wi-Fi. Nothing to buy.
Alpha for macOS and Linux · runs on your computer
Hold Talk on your phone and speak. Vispr types what you said wherever your cursor is and tidies it up as you go. Then use the same phone to move, select, fix and send, in any app or coding agent. No controller needed, though a DualSense works great too.
╭─ deepseek-v4.1-flash · session 3 ─────────
● Updated live.rs: the tick loop no longer awaits the insert task.
└ 4 files changed, 38 tests passed
›
⏵⏵ accept edits on · shift+tab to cycle
Formats as you watch
Vispr transcribes while you're still talking. When you let go, a small model made for dictation tidies the transcript: it adds punctuation, drops filler words, applies corrections like “Tuesday, I mean Wednesday”, and formats lists. The first formatted word appears about 70 ms after you let go.
Features
Scan a code once and your phone becomes a trackpad, a slide pad for the caret, the keys each mode needs and a big Talk button. It connects straight to your computer over your Wi-Fi. Nothing to buy.
Editors, browsers, chat apps and terminals. On Hyprland and macOS it cancels instead if focus moves first.
Tap the mode chip to switch between editing text, working in a terminal agent and moving around Herdr.
Slide to move the caret, hold and slide to select, then talk over the selection to replace it.
Sticks under your thumbs, its own microphone and a button for every action. Use it on its own or alongside your phone.
Speech recognition and formatting both run locally, on open models. No account, no cloud, no telemetry. Models download once and are checked against pinned checksums. Your phone talks to your computer directly over your Wi-Fi.
The tour
All on your phone. Scroll to step through each one.
Hold Talk on your phone and say it. Your words show up as you speak and are typed at the caret when you let go.
Coding agents
Vispr speaks Herdr, the terminal workspace for coding agents. It knows which pane you're talking to and who's waiting on you.
/usage and /compact.Running cargo test --workspace…
73 passed
Allow edit to src/pill.rs?
1 yes · 2 always · 3 no
Website screenshots updated.
ready for input
~/projects/vispr
›
Prefer a controller?
Everything on the phone has a button here too, plus sticks under your thumbs and the controller's own microphone. It works on its own or alongside your phone. Pick a mode to see what each control does, or watch the DualSense film.
Hover a control to find it. Options opens Vispr's settings from anywhere; Create + Options puts it in standby.
Under the hood
Everything between your voice and the caret runs locally, in Rust. The input loop never waits for the models.
Your phone's, the DualSense's or your computer's, resampled to 16 kHz in 20 ms batches.
NVIDIA's streaming speech model, through transcribe.cpp.
Superwhisper's dictation-cleanup model, reading ahead as you speak.
A persistent virtual keyboard and pointer on Linux, Accessibility events on macOS. One paste per dictation.
On Hyprland and macOS, Vispr follows window focus. If you switch away mid-sentence, it cancels instead of typing into the wrong window.
Learns your background noise from loudness alone, so the voice meter moves for you and not the fan.
Every control rule lives in one pure, unit-tested mapper, so the same input always produces the same actions.
Privacy
No audio uploads, no cloud transcription, no account. While Vispr is awake it reads only the microphone's loudness, to measure background noise. It listens to your voice only while you hold Talk (or R2), and the audio never leaves your computer. This site has no analytics and loads nothing but its own files.
A Mac with Apple silicon, or a Linux PC on Wayland: a recent x86-64, or an ARM64 machine such as a Snapdragon laptop. Hyprland (and Omarchy) is the best-tested Linux setup; GNOME and KDE support is new. Then your phone, on the same Wi-Fi. A DualSense over USB or Bluetooth is optional. About 1.2 GB of models download on first run, or none of the speech models if you've used Handy: Vispr reuses its downloads.
No. Most people use their phone. Scan the code in Vispr and add the page to your Home Screen: it becomes a trackpad, the keys each mode needs and a button you hold to talk. Voice and controls go straight to your computer over your Wi-Fi. If you have a DualSense, it adds sticks under your thumbs and its own microphone, and the two work together.
Nemotron 3.5 transcribes many languages. Smart formatting is English only for now; turn it off, or use Raw mode, for everything else.
Vispr runs on Linux and macOS. The macOS version is newer and less tested. Windows isn't planned yet.
It will be, under the MIT licence, when it's ready for a public release. Until then it's in a private alpha.
Early access
Vispr is in a private alpha for macOS and Linux. If you have an access code, enter it to download.
The easy way: one command
Paste it into a terminal on macOS, Omarchy, Arch, Ubuntu or Debian. It installs Vispr and its voice models, checks every download, and opens setup.
Or download it yourself
macOS: open the DMG and drag Vispr to Applications. It isn't signed yet, so the first time, right-click Vispr and choose Open.
Omarchy: run the command above. That's all; Vispr types through Hyprland directly.
Ubuntu and Debian: sudo apt install ./vispr_*.deb
Other Linux: chmod +x the binary and run it. It needs WebKitGTK 4.1 and a few other libraries; see the README.