# Changelog · ZenVoice

Source: https://getzenvoice.com/changelog

> Every ZenVoice release.

Changelog

# What’s new

Every ZenVoice release, starting with the first.

1.  v0.5.0
    
    Upcoming
    
    First release
    
    Private dictation for Mac: fourteen on-device models, ZenPolish 1.7B v2.2, and a notch HUD that shows your words as you speak.
    
    Added
    
    -   Press ⌃⌥Space, or hold the Globe (Fn) key, and talk: your words are typed into whatever app you're in. ⌃⌥V pastes the last dictation again.
    -   Eleven on-device speech engines: NVIDIA Parakeet TDT 0.6B V3 and V2, NVIDIA Nemotron 3.5 Multilingual, Whisper Large V3 Turbo, Small and Tiny, Cohere Transcribe, Qwen3-ASR 0.6B, Apple Speech, and Hinglish Prime for Hindi and English written as Hinglish.
    -   ZenPolish 1.7B v2.2, ZenVoice's newest formatting model: fillers and false starts out, punctuation and capitalization fixed, numbers, money and dates written the way you'd type them. On 500 held-out dictations it makes a fifth of the word errors of the stock model it's trained from.
    -   Apple Intelligence and Qwen 3.5 2B for Smart formatting too.
    -   The notch HUD, a live capsule that grows out of the camera housing, and the pill, a compact HUD that works on any display.
    -   Insert, copy only, or review before insert, and your clipboard restored after pasting.
    -   Voice snippets: say a trigger phrase and ZenVoice types the full text.
    -   Encrypted history with search, retry and a Recovery Inbox for dictations you cancelled.
    -   Insights: words per minute, app rankings, recording time and a streak calendar, all computed on your Mac.
    -   A voice profile with your own correction rules, Audio Doctor, and a Permissions screen that shows exactly what ZenVoice can access.
    -   Model downloads pinned to a reviewed revision and checked by SHA-256 before they load.
    
    Changed
    
    -   Requires macOS 15 or later. Apple Speech needs macOS 26.