Can Superscribe be vibe coded?

Build brief — a focused alternative to Superscribe

**Verdict:** Partly, if you narrow it · **Buildability:** 49/100 · **Category:** Voice Dictation

**Source:** https://www.canitbevibecoded.com/superscribe

Independent editorial assessment from Can It Be Vibe Coded? Not affiliated with, endorsed by, or derived from Superscribe. Verify current pricing and capabilities before acting.

Context

**Superscribe** — Turns calls on your existing number into CRM-ready notes, with desktop dictation and auto-matched billable time. It currently costs $38/mo.

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 substantially larger part even before telephony.

This brief describes a focused, single-operator replacement for the part of Superscribe that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.

What you are building

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.

Build a focused single-user workflow with real persistence, search, and export.

A responsive interface with real empty, loading, success, and error states.

Requirements

Functional

MacOS microphone + accessibility permissions.

Twilio account, a number, and an iOS device if you attempt the call-capture half.

Data and integrations

Streaming STT API key (ElevenLabs Scribe or Deepgram) or local whisper.cpp.

LLM API key for transcript cleanup.

Each of these needs a real account, credential, or quota. Set them up before writing feature code.

Non-functional

Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.

Security: server-side secrets, validated input, and no credentials in the client bundle.

Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.

Portability: the operator can export their data and leave without losing it.

Implementation brief

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.

Delivery standard

Inspect the repository first, then write a short implementation plan before writing code.

Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.

Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.

Include responsive layouts plus genuine empty, loading, success, validation, and failure states.

Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.

Add structured logs around every external call and return actionable errors without leaking sensitive details.

Write unit tests for the core logic and one automated test of the main user journey.

Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.

Acceptance criteria

A clean install starts the app using only the README and .env.example.

The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.

Invalid input, missing configuration, provider failure, and an empty database each have a usable state.

The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.

Tests, type checking, linting, and a production build all pass with no ignored failures.

No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.

Non-goals

Do not build these, and do not claim to have replaced them:

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.

Reliability at the vendor's scale is an operations problem, not a prompt.

Connectors, OAuth flows, and vendor API changes require constant upkeep.

What you still own after launch

Secure credentials, rotate secrets, and handle provider rate limits.

Run migrations, backups, restores, and dependency updates.

Test the critical journey after every model, API, or hosting change.

Monitor failures and fix the edge cases a first prompt will miss.

Maintain every third-party integration as APIs and OAuth rules change.

Risk

**Operational risk.** The code is achievable; dependable data, integrations, and ongoing operations are the real cost.

Editorial confidence in this assessment: high. No independent one-shot implementation is linked yet.

Prior art

Working open-source software you can read, fork, or borrow from before starting:

[Handy](https://github.com/cjpais/Handy) — MIT cross-platform push-to-talk dictation app in Tauri, built to be forked; covers the whole desktop core loop

[VoiceInk](https://github.com/Beingpax/VoiceInk) — GPL native Swift macOS dictation app with local whisper.cpp and per-app modes; closest open clone of the mac side

[FreeFlow](https://github.com/zachlatta/freeflow) — Solo-built open Wispr Flow clone; working example of cloud STT plus LLM cleanup with active-window context

[Twilio Media Streams](https://www.twilio.com/docs/voice/media-streams) — Official docs and tutorials for streaming live call audio to STT; the happy path of the call-capture half

Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/superscribe