Superscribe

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

KINDA · partial replacement
price $38/mosubscription / year $456estimated build time one sitting (dictation only), multi-week with call capturereplaced by 0 people

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.

Build verification: not recorded. How we judge buildability

What you give up

  • 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.

Your build guide

The stack, security requirements, and agent rules for a focused replacement.

Before you start

  • Runtime and tools: Swift, SwiftUI/AppKit and SQLite on macOS, with secrets in Keychain where needed.
  • Before starting: A Mac, the current Xcode toolchain and a documented permission checklist; distribution signing is a separate delivery task.
01
Swift, SwiftUI/AppKit and SQLite on macOS, with secrets in Keychain where needed
02
Data design: Store DictationSession, CapturedApp, TranscriptRevision and InsertAttempt; cancellation invalidates late callbacks and clipboard restoration happens only if no newer user copy occurred.
03
Setup: A Mac, the current Xcode toolchain and a documented permission checklist; distribution signing is a separate delivery task
engineering roadmap

Implementation plan

1

Phase 1

Pin the working slice and create its example input: Hold a hotkey to dictate, inspect a transcript, optionally review a cleanup diff and insert text into the intended app. Confirm setup: A Mac, the current Xcode toolchain and a documented permission checklist; distribution signing is a separate delivery task.

2

Phase 2

Implement persistence and write-time invariants before decorating the UI: Store DictationSession, CapturedApp, TranscriptRevision and InsertAttempt; cancellation invalidates late callbacks and clipboard restoration happens only if no newer user copy occurred.

3

Phase 3

Connect the working view to real saved state. Ask for each operating-system permission when its feature is used. Handle denial and revocation without a loop; show permission status and keep local history deletable.

4

Phase 4

Expose the app-specific limits and recovery path in context: Choose either a documented streaming provider or pinned local transcriber explicitly; never switch providers silently. Store keys in Keychain and preserve raw wording before optional model cleanup.

5

Phase 5

Walk through this concrete acceptance case and preserve its exported evidence: Release the hotkey, switch apps and cancel during cleanup; do not paste into the new app or overwrite a fresh clipboard value. Finish the README and backup/restore instructions; report unfinished capabilities explicitly.

the pro prompt
download AGENTS.md
Build the following focused alternative to Superscribe. This is a deliberately limited personal or small-team substitute, not parity with the paid service.

WORKING SLICE
Hold a hotkey to dictate, inspect a transcript, optionally review a cleanup diff and insert text into the intended app.

SETUP AND ARCHITECTURE
Use Swift, SwiftUI/AppKit and SQLite on macOS, with secrets in Keychain where needed. Prerequisites: A Mac, the current Xcode toolchain and a documented permission checklist; distribution signing is a separate delivery task. Before integrating anything, record actual versions and permissions, plus model files or provider limits only where used, in the README; make unavailable dependencies visible rather than simulating success.

DOMAIN MODEL AND INVARIANTS
Store DictationSession, CapturedApp, TranscriptRevision and InsertAttempt; cancellation invalidates late callbacks and clipboard restoration happens only if no newer user copy occurred.

IMPLEMENTATION CONTRACT
Ask for each operating-system permission when its feature is used. Handle denial and revocation without a loop; show permission status and keep local history deletable. Provide an input/setup view, the main work view, and a review/export view appropriate to this workflow. Preserve the last saved state if a job or save fails. Include empty, loading, permission-denied, partial and retryable-error states. Log identifiers and error categories without secret values or unnecessary private content.

APP-SPECIFIC BOUNDARY AND RECOVERY
Choose either a documented streaming provider or pinned local transcriber explicitly; never switch providers silently. Store keys in Keychain and preserve raw wording before optional model cleanup.

ACCEPTANCE SCENARIO
Release the hotkey, switch apps and cancel during cleanup; do not paste into the new app or overwrite a fresh clipboard value. Also reopen the app after an interrupted operation, confirm the saved record/export remains inspectable, and document the recovery action. These are implementation acceptance requirements, not a claim that this guide has been tested.

DELIVERY
Deliver a runnable repository with migrations or project-format versioning, a non-sensitive example, environment/permission setup, the exact manual acceptance steps, and a backup/export-and-restore walkthrough. Implement the working slice before optional integrations; list any deferred paid-product capabilities honestly. Do not add capabilities outside the working slice just to resemble the original product.

PROJECT RULES FOR AGENTS.md
Keep the domain invariants above executable at the write boundary. Propose scope changes before adding providers or permissions. Never fabricate source evidence, publish results, identity matches or successful delivery. Preserve user originals and require an explicit confirmation for destructive changes or external publication.

$ open in your agent (prompt prefilled, you press enter), copy the prompt or copy or download AGENTS.md

prior art · use these instead of building, if you'd ratherHandyMIT 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.↗
share on X ↗

Superscribe pricing

planmonthlyannual (per mo)what you get
superscribe pro$18/user$14.33/userDesktop dictation on Mac and Windows, AI cleanup, time tracking, templates, project context, and reports$172 billed annually; free try-now flow requires no card, but the public page gives no numeric trial duration or usage cap.
business voice$38/user$30.40/user1+ seats; pooled call minutes, existing-number routing, live transcription, AI summaries, and Pro for every seatAnnual equivalent is calculated from the page's stated 20% yearly discount; checkout total and included call-hour quantity were not publicly exposed. More than 10 seats requires sales contact.
travel pass——7 days of Superscribe Phone with included call hours$12 one-time; the numeric included-hour allowance is not stated publicly.

free tierNo 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.

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

hidden costsBusiness 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.

pricing sources checked 2026-08-14 · pricing source ↗

Questions about Superscribe

Can you build your own Superscribe with AI?

Partly. 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.

What does the Superscribe build prompt cover?

The prompt starts with this scope: Hold a hotkey to dictate, inspect a transcript, optionally review a cleanup diff and insert text into the intended app. Full-product capabilities excluded from the comparison include: 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. Follow the implementation plan and its prerequisites before expanding the build.

How do I use the prompt, AGENTS.md and agent skills?

Start with the Superscribe prerequisites and stack, then copy the prompt into your coding agent. Save the project rules as AGENTS.md in the project root. Linked skills are optional packages or source instructions for specific tasks; review their current contents and install only those matching the chosen stack. A skill does not supply API credentials or verify the finished app.

How long will this Superscribe project take?

The catalogue estimate is one sitting (dictation only), multi-week with call capture for the limited scope. Setup, integration approvals, debugging, deployment and ongoing maintenance can add time. This is an estimate, not a delivery guarantee.

What would I give up by replacing Superscribe?

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. 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.

What price is this guide comparing against?

The recorded Business Voice plan is $38/mo (monthly), checked 2026-07-30. Check the linked pricing source before buying. Building your own also has hosting, API and maintenance costs; the recorded amount is not a guaranteed saving.

What can I use instead of building Superscribe?

The prior-art section lists Handy, VoiceInk, FreeFlow, Twilio Media Streams as starting points. Review their current scope, license and maintenance before adopting one.

Every week, more subscriptions die.

New verdicts, new prompts, the week's most-doomed apps.
One email. Unsubscribe in one click.

last week:100 Questions · KINDA1of10 · KINDA1Password · KINDA+1090 more

free forever · no scanner spam · the prompt stays on the site, the deaths come to you

$weekly: what got a verdict, what died.