Skip to main content
AIDiveForge AIDiveForge
Visit KeyVox

Share This Tool

Compare This Tool
📋 Embed this tool on your site

Copy this code to embed a compact tool card:

KeyVox

FreemiumSelf-Hosted

Summary

Built-in dictation on Mac and iOS ships your voice to Apple's servers, and on slower machines it makes you wait — KeyVox routes every word through an on-device Whisper or Parakeet model instead, with no network hop and no subscription clock running.

KeyVox installs as a keyboard on iOS and a menu-bar app on macOS, transcribes via downloaded AI models (~190 MB for Whisper, ~480 MB for Parakeet), and writes text into any app the moment you release the trigger key. The Vibes feature applies reversible writing styles after dictation — so you can rephrase a casual voice note into a formal email without re-dictating. The Speak module reads copied text aloud using on-device voices. Where it breaks: KeyVox is a dictation keyboard, not a manual typing keyboard, so users who want to mix voice and touch typing in the same session have to switch back to their system keyboard constantly. Intel Mac support exists, but Apple Silicon is the architecture this runs well on.

Bottom line: Pick KeyVox if you dictate frequently on Apple Silicon and refuse to send voice data to a cloud — but if you need a general-purpose keyboard you can also type on, or you're running older Intel hardware and want consistent speed, you'll be working around its limits from day one.

Pricing Plans

Free Tier
2 free Speaks per day; unlimited core dictation

Free

Free

Core dictation, transcription, and 2 free Speaks per day

  • On-device processing
  • Vibes styles
  • iCloud sync

Speak Unlimited

per month

One-time purchase to remove daily Speak limit

  • Unlimited text-to-speech

View full pricing on keyvox.app →

Pricing may have changed since last verified. Check the official site for current plans.

Community Performance Report Card

No community ratings yet. Be the first to rate this tool!

Best For: Users prioritizing privacy and local processing, Mac and iOS users needing fast dictation, Multilingual on-device transcription, No-subscription voice input tools

Community Benchmarks Community

No community benchmarks yet. Be the first to share a real-world data point.

  • All transcription runs on-device with zero network requests, so sensitive dictation — legal notes, medical records, anything you would not paste into a web form — never touches a third-party server.
  • Hold-to-record, release-to-transcribe on macOS means text appears without a delay loop, so you stay in flow instead of watching a spinner after every sentence.
  • Reversible Vibes styles let you apply or swap a writing tone after dictating, so you do not have to re-record when the first draft's register is wrong.
  • iCloud sync for the custom dictionary means a name or technical term you train on Mac appears on iOS without manual re-entry, so your vocabulary carries across devices.
  • Support for both Whisper and Parakeet models with multi-lingual capability means you are not locked to one transcription engine or one language if your workflow spans both.
  • KeyVox is not a full keyboard — on iOS it has no ABC input layer, so any session where you need to mix typed and dictated text requires switching keyboards back and forth; teams that want a single keyboard handling both modes will abandon this for a dictation tool layered on top of their existing keyboard.
  • Performance scales with Apple Silicon; the vendor explicitly notes Intel Macs are supported but recommends Apple Silicon for maximum performance — on older Intel hardware, transcription of longer passages slows noticeably, and teams still on pre-M1 machines will find a cloud-based dictation service faster in practice.
  • There is no API and no self-hosted server deployment path, so developers who want to pipe dictation output into a pipeline or trigger transcription programmatically have no integration surface — teams building voice-to-action workflows will need a different engine entirely.

Community Reviews

No reviews yet. Be the first to share your experience.

About

Platforms
macOS, iOS
API Available
No
Self-Hosted
Yes
Last Updated
2026-07-01T20:47:32.709Z

Best For

Who it's for

  • Users prioritizing privacy and local processing
  • Mac and iOS users needing fast dictation
  • Multilingual on-device transcription
  • No-subscription voice input tools

What it does well

  • Dictate text into any app on Mac or iOS
  • Transcribe speech privately without internet
  • Convert text to spoken audio on-device
  • Apply reversible writing styles to dictated content

Discussion Community

No discussion yet. Sign in to start the conversation.

Spotted incorrect or missing data? Join our community of contributors.

Sign Up to Contribute

Community Notes & Tips Community

Be the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.

Frequently Asked Questions

Is KeyVox free?
KeyVox has a permanent free tier alongside paid upgrades. You can keep using a baseline version indefinitely without paying.
Is KeyVox open source?
No — KeyVox is a closed-source tool. Source code is not publicly available.
Can I self-host KeyVox?
Yes. KeyVox supports self-hosting on your own infrastructure.
What platforms does KeyVox support?
KeyVox is available on: macOS, iOS.

Hours Saved & ROI Stories Community

Be the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."

KeyVox

KeyVox is a voice dictation tool for macOS (13.5+ with Whisper; 14+ with Parakeet) and iOS (18.6+), built by independent developer Dom Esposito. The core workflow: hold a modifier key to record, release to transcribe. Text appears in whatever app has focus — notes, email, a code editor, anything. All processing runs on the local device after a one-time model download; the vendor states no data ever leaves the device and no cloud processing occurs at any point.

The differentiating feature is KeyVox Vibes — on-device, reversible writing styles applied to dictated content. You speak naturally, pick a style (formal, casual, list format, and others), and the rewrite happens locally. Crucially, the style is reversible: change your mind after the fact without re-dictating. The Speak module inverts the flow — copy any text, and on-device AI voices read it aloud in up to eight voices, also without a network connection.

KeyVox fits users who dictate into desktop and mobile apps daily and treat privacy as a hard requirement, not a preference. It also fits multilingual users — the vendor cites multi-lingual support across both model options. Where it does not fit: it is not a full keyboard. The iOS version is explicitly designed for dictation first; users who want to mix voice input with touch typing must switch keyboards mid-session. Intel Mac support exists, but the vendor recommends Apple Silicon for performance — teams on older hardware will notice the difference under load.

The custom dictionary syncs across macOS and iOS via iCloud, covering names, emails, and domain-specific terms. Automatic list and paragraph formatting is built in. The Speak feature is noted as a paid-only feature within the app (one-time purchase for unlimited use), while core dictation is free with no subscription required.