[verdict][curated prompt][source: superscribe.io]

Can I vibecode Superscribe?

// buildable in a weekend, but real gaps stay open

The desktop dictation half is a solved one-sitting build with complete open-source clones to fork. The hero product is not that: live-transcribing calls on your existing iPhone number takes carrier call forwarding, a pooled Twilio number, a CallKit/PushKit softphone, and a dual-track media-stream pipeline that can only be debugged against live phone calls. And a clone gets you a transcript file, not the workspace around it: roughly 45k lines of API and web app that embed every recording, time block, and project (with synced GitHub repo context), auto-file notes and billable time to the right client, and expose it all as reports, semantic search, a public API, and an MCP server. Each piece is a documented recipe; shipping all of them integrated is the multi-week part even before telephony.

confidence: high

what it is: Turns calls on your existing number into CRM-ready notes, with desktop dictation and auto-matched billable time

Buildability index · an editorial game

Price 38 $/month weight: plus 3
Time one sitting (dictation only), multi-week with call capture weight: minus 2
Category voice dictation no weight
Moat infrastructure scale · integrations · execution quality weight: minus 4
Confidence high weight: plus 1
What you lose 5 items weight: minus 2
Site superscribe.io (si apre in una nuova scheda) no weight

think twice

The moat outweighs the price: rebuilding this is a project, not an evening.

Gioco editoriale: il verdetto dice se un agente può, l’indice se conviene.

What you build

Bind a global hotkey, stream mic audio to a realtime STT API, run one LLM cleanup pass, and paste the result into whatever app has focus.

what you need

macOS microphone + accessibility permissions
streaming STT API key (ElevenLabs Scribe or Deepgram) or local whisper.cpp
LLM API key for transcript cleanup
Twilio account, a number, and an iOS device if you attempt the call-capture half

Half of it is a superwhisper-shaped yes; the existing-number phone rail drags the whole product to kinda.

The prompt

A weekend with a coding agent. The gaps that stay are right below, under “what you lose”.

One-shot prompt EN

Build me a push-to-talk dictation tool for macOS to replace Superscribe's desktop app.
Requirements:

- Swift menu bar app, SPM only, no Xcode project. A global hotkey (default: hold
  Option+Space) records while held, stops on release.
- Capture the mic with AVAudioEngine, downsample to 16kHz mono PCM, and stream it
  over WebSocket to ElevenLabs Scribe realtime (key in .env). Show partial
  transcripts in a small floating panel while I speak.
- On release, run one LLM cleanup pass over the final transcript (fix punctuation,
  drop filler words; key in the same .env), then paste it into the focused app via
  NSPasteboard + CGEvent Cmd-V and restore my previous clipboard afterwards.
- Fallback: with no ElevenLabs key, record to a temp wav and transcribe locally
  with whisper.cpp instead. Slower is fine.
- Menu bar icon shows idle/recording/transcribing states; a history window lists
  the last 20 transcripts with copy buttons, persisted to ~/Dictation/history.jsonl.
- Ad-hoc codesign for my own machine only. README documents the Microphone and
  Accessibility permission prompts and the whisper.cpp model download.
- Out of scope: live word-by-word typing into the field (paste on release only),
  Windows support, accounts and billing, and the phone-call capture product. If I
  want call notes I will upload recordings by hand.

Curated prompt: written and reviewed by hand for this app. In English on purpose — it is the language coding agents work best in.

What you lose

call capture on your existing number (carrier forwarding into a CallKit softphone)
glitch-free live word-by-word insertion tuned per app: terminals, Electron editors, browser contenteditables
auto-filing: dictations and calls alike are matched to the right project via embeddings (enriched with GitHub repo context) plus live commit activity during the work block, so billable time lands on the right client without tagging
the workspace around the transcripts: semantic search, invoice-ready PDF reports, CRM note drafts, a public API, and an MCP server
Windows parity and signed, notarized auto-updating installers

Why people still pay

They pay for the phone rail (answer calls normally on the number they already have, no bot, no second device) and for everything downstream arriving pre-filed: transcripts semantically matched to the right client and project using their own GitHub activity as context, then turned into searchable history, invoices, and CRM drafts.

moat: Infrastructure scale Integrations Execution quality what a moat is

telephony infrastructure/integrated workspace breadth

Who has already built it

Starting from here is still vibecoding: the prompt is for when you want it exactly your way.

Handy (opens in a new tab) — MIT cross-platform push-to-talk dictation app in Tauri, built to be forked; covers the whole desktop core loop. (alive)
VoiceInk (opens in a new tab) — GPL native Swift macOS dictation app with local whisper.cpp and per-app modes; closest open clone of the mac side. (alive)
FreeFlow (opens in a new tab) — Solo-built open Wispr Flow clone; working example of cloud STT plus LLM cleanup with active-window context. (alive)
Twilio Media Streams (opens in a new tab) — Official docs and tutorials for streaming live call audio to STT; the happy path of the call-capture half. (alive)