Documents and notes decision
Voys
A technically capable developer can assemble an offline, local-first replacement in about a week using existing open-source ASR projects; Voys' main value (device-first Turkish transcription and formatting) is reproducible with available prior art.
Visit website↗Built by Ozer SUBASI, who ships 4 products in this index
Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$100one-off32 h to build
$0/mo3 h/mo upkeep
No published price to break even against.
Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Voys alternatives, with the arithmetic →
What a replacement has to do
- Record voice → device speech-to-text (Turkish) → auto-format into paragraphs/dialogue → autosave locally → edit/export or send text to user's LLM account for reformatting.
What it still won’t have
- Polish and UX refinements of a shipped product (animations, onboarding flows)
- Ongoing commercial support and beta user feedback loop
- Broad multi-language models and managed model updates
- Brand, discovery, and any closed-source optimizations the vendor may add
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Voys does not publish a price we could read, so there is nothing to compare against. What building costs is below.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal offline-first speech-to-text note app using Electron (desktop) or Tauri + React, with a native bridge to ggml-org/whisper.cpp for on-device Turkish ASR. Core features in scope: microphone capture with streaming to whisper.cpp, voice-command-to-punctuation mapping, autosave-by-paragraph to local filesystem (or IndexedDB), an editor UI to view/edit/reorder paragraphs, and an optional "Format with LLM" export that posts plaintext to a user-provided ChatGPT/Claude API key (the app must never store that key server-side). Out of scope: cloud sync, multi-user accounts, multi-language support beyond Turkish, and hosted backend. Include error handling for audio device failures, model-load failures, disk-write errors; include unit tests for the punctuation parser and integration tests that run a short audio file through the pipeline; provide packaging scripts for macOS and Windows.
How we checked
How the score was reached
- Build verdict base78
- An open-source build was found+5
- 5 cited sources+3
- 3/3 assessment runs agreed+4
- Evidence score90
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 5
Every page the run actually retrieved.
- official productVoys — Konuş, kitap gibi yazılsın (product page)
- official productVoys — İnternet gerekir mi? (product page)
- official productVoys — Verilerim nereye gidiyor? (product page)
- open sourcecjpais/Handy
- open sourceZackriya-Solutions/meetily
Integrity checks
What held up, and what did not.
