AI assistants and search decision
Sayso
A single capable developer can build a usable local replacement in about one week using open-source ASR projects, losing only the vendor's polished UX, hosted models, and paid support.
Visit website↗$12/mo
$144/yr
Read off the official pricing page.
$100one-off40 h to build
$0/mo4 h/mo upkeep
On cash alone, building overtakes the subscription at 1 seat.
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 Sayso alternatives, with the arithmetic →
What a replacement has to do
- Capture microphone audio, transcribe to text, post-process to remove filler/auto-edit/format, inject or paste text into the active text field, persist personal dictionary
What it still won’t have
- Proprietary hosted models and any cloud-side optimizations
- Polished commercial UX, priority feature roadmap and official support
- Cross-platform polished installers and code-signed binaries unless you pay for signing services
- Any proprietary performance or latency optimizations performed by the vendor
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 1 seat.
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 cross-platform desktop dictation app (Electron + Node backend) that captures microphone audio, runs local ASR using faster-whisper or whisperX for transcription, applies post-processing to remove filler words and self-corrections and to auto-format lists/steps, supports a personal dictionary UI with persistent storage (SQLite), and pastes/injects the edited text into the active text field (clipboard + virtual keystroke fallback). In scope: hotkey/start-stop recording, realtime partial transcripts, final post-processed export, basic settings, Mac and Windows packaging. Out of scope: hosted cloud transcription, team/multi-user sync, advanced telemetry. Include error handling for model load failures, tests for transcription pipeline and post-processing logic, and CI that builds signed installers (stubs for signing if no key).
How we checked
How the score was reached
- Build verdict base78
- An open-source build was found+5
- 5 cited sources+3
- Price verified on pricing page+3
- Evidence score89
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 productSaySo - AI Voice-to-Text Assistant for Mac & Windows
- official productSaySo Use Cases - Notion, Jira, Linear and More
- official pricingSaySo - Free and Pro Plans
- open sourceszczyglis-dev/py-gpt
- open sourcemoonshine-ai/moonshine
Integrity checks
What held up, and what did not.
