[verdict][generated prompt][source: superwhisper.com]
Can I vibecode Superwhisper?
// one session, and a personal version you can actually use
A push-to-talk recorder that transcribes and pastes text into the active app is very buildable for one person, especially on macOS.
confidence: high
what it is: AI dictation for Mac that turns speech into text anywhere
Buildability index · an editorial game
- Price 8.49 $/month weight: plus 1
- Time one sitting weight: plus 3
- Category voice dictation no weight
- Moat execution quality weight: minus 1
- Confidence high weight: plus 1
- What you lose 5 items weight: minus 2
- Site superwhisper.com (si apre in una nuova scheda) no weight
The maths works, but not by much: look at what you lose before you start.
Gioco editoriale: il verdetto dice se un agente può, l’indice se conviene.
// free tier: A free version covers basic dictation; Pro adds unlimited cloud and local models.
What you build
Bind a hotkey, capture microphone audio, transcribe with Whisper or speech API, optionally rewrite with an LLM, and paste into the active field.
what you need
- macOS automation/accessibility permissions
- speech API or local Whisper
- optional LLM API
- hotkey library
Strong yes and very on-brand for vibecoding: small utility, obvious primitives, high subscription annoyance.
The prompt
One session with a coding agent and your version runs.
Build me a push-to-talk dictation tool for macOS to replace Superwhisper. Requirements:
- A global hotkey (default: hold right Option) records my mic while held, stops on
release. A small Swift menu bar app or a Hammerspoon script, pick the simpler to
ship.
- Record with ffmpeg (avfoundation) to a temp wav, transcribe locally with whisper.cpp
(small.en by default, model path in a config file). Works fully offline, no cloud
speech APIs.
- Paste the result into whatever field has focus (simulate Cmd+V via CGEvent or
osascript, then restore my previous clipboard).
- Optional cleanup mode on a second hotkey: send the transcript to an LLM (key in
.env) to fix punctuation and drop filler words, then paste. If no key is set, this
mode just does a plain paste.
- Menu bar icon shows idle/recording/transcribing; clicking it lists the last 10
transcripts with copy buttons.
- Append every transcript to ~/Dictation/YYYY-MM.md with a timestamp, and delete the
audio after transcription. No accounts, no telemetry.
- Out of scope: per-app presets and custom vocabulary tuning. One good general mode.
- README: mic + accessibility permissions to grant, how to download the whisper
model, and a note that the first run will trigger macOS permission prompts.Prompt generated from the data on this page, not reviewed by hand yet. In English on purpose — it is the language coding agents work best in.
What you lose
- beautiful native UX
- presets
- vocabulary/profile tuning
- app-wide polish
- support
Why people still pay
They pay for the low-friction menu-bar experience and dictation profiles.
moat: Execution quality what a moat is
polish/native integration
Free alternatives
Not in the mood to build it? These already exist, they are free or open source, and we checked them one by one.
Rejected (1) — and why
- VoiceInk (si apre in una nuova scheda) — The code is open, but the usable download is a trial; the free path is compiling it yourself in Xcode.
Who has already built it
Starting from here is still vibecoding: the prompt is for when you want it exactly your way.
- whisper.cpp (opens in a new tab) — Local transcription engine that makes a simple dictation clone realistic. (alive)
Do you agree?
The vote balance
Ancora nessun voto: il tuo è il primo.
Nessun voto ancora — il primo pesa.
