Wave 1 beta • macOS 14+ • Apple Silicon

Dictate.
Locally.
Instantly.

Press a key, speak naturally, text appears - anywhere on your Mac. Powered by Parakeet TDT on the Apple Neural Engine. Zero cloud. Zero subscription tax.

Download Free Trial View Pricing

4x faster than typing

Typing ~40 WPM
40 WPM
evoglyph ~180 WPM
180 WPM

85ms speech-to-text latency on the Apple Neural Engine. See the benchmark →

Recording

Raw voice input

um so basically I think we should uh refactor the the useEffect hook because its like causing a memory leak when the component unmounts and uh yeah we need to clean up the subscription

Cleaned by evoglyph

Clean output

Refactor the useEffect hook - it's causing a memory leak when the component unmounts. We need to clean up the subscription on cleanup.

Simple by design

Three steps. Zero setup.

From install to first word in under two minutes. Works in any Mac app you already use.

01

Tap

Press Fn or your custom hotkey to begin recording. A subtle indicator appears in your menu bar.

02

Speak

Talk naturally, including technical jargon. TypeScript, GraphQL, Kubernetes - spelled correctly, every time.

03

Done

Text appears in your focused app. No copy-paste, no window switching. Release the key, your words are there.

Built for developers

Everything you need.
Nothing you don't.

Purpose-built for people who care about privacy and spend their day in terminals and editors.

Fully Local

All processing happens on your Mac. No cloud required. Your audio never leaves your device - not even in anonymized form.

AI Cleanup

A built-in local LLM removes filler words and fixes punctuation - without rewriting your voice. Runs entirely on your Mac, no separate install.

Developer Vocabulary

Custom word lists prime the transcription engine. useEffect, gRPC, Zustand - spelled right, no training required.

Works Everywhere

iTerm, Obsidian, Chrome, Cursor, Slack - any Mac app. Three injection methods ensure compatibility across native and Electron apps.

Native & Lightweight

Pure Swift. Single binary. Menu bar daemon. Under 200MB with model loaded. No Electron, no runtime, no background update checks.

Custom Hotkeys

Map dictation to any key combo. Push-to-talk on Fn, hands-free toggle on F5, or whatever fits your flow. System-reserved combos are flagged before you save.

Compatible with your stack

Works in every app you use

Slack
VS Code
Cursor
iTerm2
Obsidian
Chrome
Safari
Claude
ChatGPT
Linear
Notion
Notes
Bear
GitHub
Terminal
Figma

Where it shines

Built for the way
you actually work.

Dictation stops feeling awkward the moment the tool respects the text you're writing. Here's where evoglyph earns its keep.

Commit messages & PR descriptions

Describe the change out loud and let evoglyph type it into the terminal, GitHub, or Linear. Developer vocabulary keeps useEffect, Dockerfile, and kubectl spelled correctly every time.

$ git commit -m "fix race condition in useAuth hook when token refresh coincides with logout"

Slack messages & team updates

Stop context-switching to type a three-line reply. Hold the hotkey, speak, release - the message is already in the Slack input box, cleaned up and ready to send.

#eng-backend heads up - rolling out the new auth middleware to staging in about 10 min. will post numbers when I have them.

Obsidian notes & second brain

Capture fleeting thoughts at the speed you think them. evoglyph drops cleanly formatted markdown into Obsidian, Bear, or Apple Notes - perfect for meeting summaries, research snippets, and end-of-day journals.

## Standup notes
- finished the billing migration, deployed to prod
- started on the webhook retry logic
- blocked on API keys from Stripe

Design docs & long-form writing

Talk through a design doc or RFC out loud. evoglyph's local cleanup removes ums and false starts so your first draft actually reads like prose. Takes ten minutes instead of an hour.

# RFC-042: Eventual consistency for user profile reads
## Context
Profile reads currently hit the primary DB 4M+ times per day...

How we stack up

Compare

The only local-first dictation tool built specifically for developers.

Feature
evoglyph from $1/mo
WisprFlow $14.99/mo
Superwhisper $11.99/mo
OpenWhispr Free (open source)
Local processing ✓ Partial Partial ✓
Developer vocabulary ✓ ✕ Limited ✕
Open cleanup prompt ✓ ✕ Limited ✕
Native macOS app ✓ ✓ ✓ ✕
AI cleanup Local (built-in) Cloud Cloud ✕
Works in all apps ✓ ✓ ✓ Limited
Lifetime purchase option ✓ ✕ ✕ N/A

No subscription surprises

Simple pricing

Start free. Stay if you love it. Own it forever if you want.

Monthly

Flexible, cancel anytime

$1 /month
  • Full access to all features
  • Developer vocabulary packs
  • Local AI cleanup
  • Cancel anytime
Get Started
Most Popular

Annual

Best value for power users

$5 /year
Save 58%
  • Full access to all features
  • Developer vocabulary packs
  • Local AI cleanup
  • Priority support
Get Started

Lifetime

Pay once, yours forever

$9
one-time payment
  • Full access to all features
  • All future updates included
  • No subscriptions, ever
  • Priority support
Get Started

3,000 words free • No credit card required • Cancel anytime

Verifiable privacy

Your voice stays
on your Mac.

Every claim is specific and verifiable. Don't take our word for it - check for yourself.

Local transcription only

Transcription makes 0 outbound connections. Your audio stays in memory on your machine.

Verify: Open Little Snitch or Activity Monitor during transcription.

On-device processing

Audio is processed by the Apple Neural Engine via Parakeet TDT. Never touches a server, not even ours.

Verify: Check Activity Monitor for ANE usage during transcription.

No telemetry

No analytics, no crash reports containing audio, no usage tracking of any kind.

Verify: Monitor network with Wireshark or Charles Proxy.

Disk safety

Audio buffers are processed in memory and never written to disk. Transcription history is stored in your local app sandbox - delete it any time from Settings.

Verify: Inspect app sandbox with fs_usage during transcription.

Four network calls, all listed

License activation, license re-validation, Sparkle update check, and a one-time model download on first launch. That is the complete list. See the privacy page for what each one sends.

Verify: Watch outbound traffic in Little Snitch or Activity Monitor.

Platform commitment

Built exclusively for Mac

We build one app for one platform, and make it exceptional.

Native Swift

No Electron, no runtime. Pure Swift for instant response and minimal resource usage.

Apple Neural Engine

Transcription runs on dedicated ML hardware, not your CPU. Battery-friendly and fast.

Native install

Pure Swift binary, ~150MB. Models download once on first launch and stay on your Mac. No runtimes, no bundled browsers.

Menu bar daemon

Always available, never in the way. No dock icon, no windows to manage.

Start dictating
in minutes.

The first 3,000 words are free. No account, no credit card.

Download for macOS

macOS 14+ • Apple Silicon • ~3 GB model download on first launch

Questions

FAQ