How evoglyph works, what it costs, and exactly where your audio goes. Can’t find
it?
Email support.
Getting started
macOS 14 (Sonoma) or later on an Apple Silicon Mac (M1 or newer). evoglyph runs
on the Apple Neural Engine, so Intel Macs are not supported. AI cleanup is built
in - no separate runtime to install.
The app installer is about 150MB. On first launch, evoglyph downloads the local
transcription model (~2.6GB) and cleanup model (~1.5GB) in the background. Once
they're on disk, every dictation runs locally - no further downloads, no server
round-trips.
Any Mac app. evoglyph uses three injection methods: Accessibility API splice for
native apps, keystroke injection for terminals, and pasteboard for browsers and
Electron apps. We have verified compatibility with iTerm2, Obsidian, Chrome,
Firefox, Cursor, VS Code, Slack, Linear, Notion, and all standard Apple apps. If
an app accepts keyboard input, evoglyph works in it.
Parakeet TDT on the Apple Neural Engine matches cloud-grade quality on developer
dictation. Latency is typically well under 500ms for short sentences. We ship
parakeet-tdt-v2 by default.
English. evoglyph is validated end-to-end — transcription plus AI cleanup — on
English. The underlying speech engine ships a 25-European-language variant
(Parakeet TDT v3), but the full pipeline has not been validated on those
languages, so we do not claim non-English support. Non-English support will be
advertised if and when our eval harness publishes non-English results.
Privacy & security
All dictation transcription and cleanup stays on device — your audio never
leaves your Mac. The only network calls evoglyph makes are: (1) model downloads
over HTTPS from HuggingFace on first launch only — after that, every dictation
is fully offline; (2) license activation and periodic re-validation with
evoglyph's licensing service at evoglyph.com; (3) Sparkle update checks against
evoglyph.com; (4) first-party crash and error reports to evoglyph’s own
servers, but only if you explicitly opt in via
Settings → Diagnostics — no third-party telemetry
vendor. See
the full network event breakdown.
Your audio and transcribed text never leave your device. The four network calls
evoglyph makes are: model downloads (HuggingFace, first launch only), license
validation (evoglyph.com), Sparkle update checks (evoglyph.com), and opt-in
first-party crash and error reports (evoglyph’s own servers — no
third-party telemetry vendor). See
the event-by-event breakdown.
Yes. After the initial model download, every dictation runs fully offline. The
only online dependencies are the one-time model download, periodic license
re-validation, and the optional crash-report opt-in. See
the full breakdown.
We recommend against it. evoglyph automatically skips
native macOS secure fields — when the focused element is a
native password box, dictation is refused and nothing is typed. But in
web browsers and some apps, a password field can't always be
detected, so evoglyph can't guarantee it will skip them; treat browser password
fields as unprotected. Dictation also runs through speech recognition and an AI
cleanup pass, both non-deterministic
— the inserted text may not exactly match what you said. For both reasons, type
passwords and other secrets manually rather than dictating them. See
how text injection works.
No — evoglyph is proprietary, commercial software. The privacy guarantee comes
from the local-first architecture, not source availability. Audio processing and
AI cleanup run on-device with no cloud round-trip. See
where your audio goes.
Using evoglyph
Your text lands in the app where you started recording, not
wherever focus is when you stop. evoglyph captures the target at the moment the
hotkey goes down: the AX-splice path writes to the element captured at recording
start; the pasteboard path posts Cmd+V to that app’s process ID. Switching
focus mid-dictation does not redirect your words. If injection fails entirely,
evoglyph copies the text to your clipboard and shows a notification. See
how text injection works
for more detail.
The evoglyph roadmap lists what’s in progress, planned, and under
investigation at
docs/roadmap.html. Entries are issue-cited; no dates are promised.
Pricing & licensing
The trial allows up to
3,000 transcribed words within 7 days of first launch,
whichever expires first — no account required. Early-access participants can
redeem their invite code for discounted pricing at checkout; see
the redemption walkthrough.
Standard pricing is $2/mo, $10/yr, or $20 lifetime. Early-access cohorts get a
discount on those prices - your code shows the exact amount at checkout. Same
product, same features, just the cohort price.
Walkthrough here.
Paste your code at checkout when you upgrade from the free trial - the discount
is applied automatically. Private early-access invites include your code; public
promo codes are announced on evoglyph's social channels when a cohort opens. See
the redemption walkthrough
for the full flow.
Yes. A discounted subscription keeps its rate for as long as the license stays
continuously active, and a discounted lifetime license is yours forever. When a
cohort window closes, pricing returns to standard for new customers only.
More on the cutoff and Founders perks.
Each license covers two active devices. To use evoglyph on a
third Mac, deactivate one of your existing devices from
Settings → License → Devices. Self-deactivation works
remotely — the old device does not need to be online. Full details at
docs/licensing.html.
You can cancel a subscription at any time by emailing [email protected];
access continues until the end of the current billing period. For refunds, email
[email protected]
within 30 days of purchase. Full details at
docs/licensing.html.