Un proyecto de Mauricio Gallmur· el prompt es gratis · si quieres que un agente lo corra solo, eso es lo que instalo

¿Puedo vibecodear Superscribe?

PARCIAL · un fin de semana
precio $38/mesahorrarías $456/añotiempo de build una sentada (dictation only), varias semanas with call capturecategoría 🗣️ dictadoreemplazada por 0 personas

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.

el prompt
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.

$ ábrelo en tu agente (prompt listo, tú das enter) o cópialo crudo

por qué la gente sigue pagando

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.

qué pierdes

xcall capture on your existing number (carrier forwarding into a CallKit softphone)

xglitch-free live word-by-word insertion tuned per app: terminals, Electron editors, browser contenteditables

xauto-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

xthe workspace around the transcripts: semantic search, invoice-ready PDF reports, CRM note drafts, a public API, and an MCP server

xWindows parity and signed, notarized auto-updating installers

arte previo · úsalo en vez de construir, si prefieresHandyMIT cross-platform push-to-talk dictation app in Tauri, built to be forked; covers the whole desktop core loop.VoiceInkGPL native Swift macOS dictation app with local whisper.cpp and per-app modes; closest open clone of the mac side.FreeFlowSolo-built open Wispr Flow clone; working example of cloud STT plus LLM cleanup with active-window context.Twilio Media StreamsOfficial docs and tutorials for streaming live call audio to STT; the happy path of the call-capture half.
compartir en X ↗"Acabo de reemplazar Superscribe ($38/mes) con un prompt"
los números

Precio de Superscribe

planmensualanual (por mes)qué incluye
superscribe pro$18/usuario$14.33/usuarioDesktop dictation on Mac and Windows, AI cleanup, time tracking, templates, project context, and reports
business voice$38/usuario$30.40/usuario1+ seats; pooled call minutes, existing-number routing, live transcription, AI summaries, and Pro for every seat
travel passa medida7 days of Superscribe Phone with included call hours

plan gratisNo permanent free tier verified; Pro has a no-card try-now flow, but the official page publishes neither a trial duration nor a numeric usage allowance.

facturaciónPro monthly or $172/year; Business Voice monthly or yearly at a stated 20% discount; Travel Pass is a one-time 7-day purchase

costos ocultosBusiness Voice's pooled call-minute quantity and overage treatment are not publicly disclosed. More than 10 seats moves to sales; Travel Pass also hides its included call-hour number.

verificado 2026-08-14 · fuente ↗

preguntas
¿Puedo vibecodear Superscribe?

Parcial. El núcleo de Superscribe se arma en un fin de semana con el prompt de esta página, pero hay huecos reales: 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. Lee la lista honesta arriba antes de comprometerte.

¿Cuánto cuesta Superscribe?

Superscribe cuesta unos $38/mes (Business Voice, revisado 2026-07-30), o sea $456 al año.

¿Qué pierdo si reemplazo Superscribe?

Con honestidad: 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. Si alguno de esos te sostiene el negocio, sigue pagando.

¿Hay una alternativa open source a Superscribe?

Sí: Handy (MIT cross-platform push-to-talk dictation app in Tauri, built to be forked; covers the whole desktop core loop.), VoiceInk (GPL native Swift macOS dictation app with local whisper.cpp and per-app modes; closest open clone of the mac side.), FreeFlow (Solo-built open Wispr Flow clone; working example of cloud STT plus LLM cleanup with active-window context.), Twilio Media Streams (Official docs and tutorials for streaming live call audio to STT; the happy path of the call-capture half.). Usar arte previo también es vibecodear; el prompt es para cuando la quieres exactamente a tu modo.

Cada semana mueren más suscripciones.

Veredictos nuevos, prompts nuevos, las apps más condenadas de la semana.
Un correo. Te sales en un clic.

gratis para siempre · sin spam · el prompt se queda en el sitio, las muertes te llegan a ti

$semanal: qué recibió veredicto, qué murió.