VocaWin 0.2.1-beta
App version and tag are aligned as 0.2.1-beta / v0.2.1-beta. This GitHub
Release is Latest, not a prerelease, so it shows on the repo homepage.
What changed since v0.2.0-beta
- Short dictations transcribe faster: Whisper no longer spends decode tokens
on segment timestamps for takes up to 30 s (30–50% quicker on CPU, same
text). Longer takes keep timestamps so the long-form seek loop still cuts
between words. - The Debug view now shows Whisper's load, timing, and CPU-fallback lines
live instead of only after a refresh. - vocawin.com no longer lists MSI for beta cuts, matching what the tagged
builds ship.
Hold Right Alt (or your hotkey) and talk. Text lands where the caret already
is. After a model is on disk, audio and speech-to-text stay on this PC.
Still a beta tester build. The NSIS setup is unsigned, so Windows will say
the publisher is unknown. Click More info, then Run anyway if you trust this
GitHub Release. vocawin.com points here.
NSIS is a current-user setup. MSI is paused for X.Y.Z-beta cuts.
Need today's main instead? The nightly is an unsigned NSIS build from main.
Use this tag if you want the named cut.
Open Models and download an engine before the first take. Whisper Tiny is
the usual start.
Something broken? Open an issue. Discord is discord.gg/t6muquAJbm.