Build Superscribe
KINDAreplaces $38/mosaves $456/yrback to the verdict
Before step 1
you will 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
Delivery order
Scaffold the smallest runnable application and document its commands.
done whenThe project starts from a documented command in a clean checkout.
Implement the primary data model and core workflow.
done whenThe main object can be created, read and changed end to end.
Add validation, safe failure states, and persistence.
done whenBad input is refused with a readable message and nothing is left corrupted.
Cover the critical path with automated tests.
done whenThe highest-risk behavior fails the suite when it breaks.
Exercise a clean install from the README and fix every missing step.
done whenA fresh clone reaches the first successful workflow using only the README.
That is the whole plan for Superscribe. What it deliberately does not cover is below · check the gaps before you call it a replacement.
- 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
Need the files? The project pack on the verdict page hands your agent the whole brief · more dictation.