<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Ditto — Changelog</title><description>Local voice-to-text for Windows. Release notes for every Ditto version.</description><link>https://dittotalks.com/</link><language>en-us</language><item><title>v1.0.0 — First public release</title><link>https://dittotalks.com/changelog#v1.0.0</link><guid isPermaLink="true">https://dittotalks.com/changelog#v1.0.0</guid><description>&lt;p&gt;&lt;strong&gt;MAJOR&lt;/strong&gt;&lt;/p&gt;&lt;h4&gt;Added&lt;/h4&gt;&lt;ul&gt;&lt;li&gt;Local voice-to-text transcription with whisper.cpp, no audio leaves the machine&lt;/li&gt;&lt;li&gt;Floating pill with click-through, drag, and always-on-top&lt;/li&gt;&lt;li&gt;Tray app lifecycle: close hides the pill, quit only from the tray menu&lt;/li&gt;&lt;li&gt;Global shortcut (Ctrl+Shift+Space by default, fully configurable)&lt;/li&gt;&lt;li&gt;Auto-paste to the active window with optional clipboard restoration&lt;/li&gt;&lt;li&gt;Settings window with seven panels: General, Shortcut, Audio, Appearance, Models, Advanced, About&lt;/li&gt;&lt;li&gt;Five pill themes (Matte, Onyx, Aurora, Sunset, Mint) with voice-reactive bars on the colored ones&lt;/li&gt;&lt;li&gt;Eight UI languages with system auto-detect (EN, ES, FR, DE, IT, PT, JA, ZH)&lt;/li&gt;&lt;li&gt;On-demand model download with progress and cancel: Tiny, Base, Small, Medium, Large-v3&lt;/li&gt;&lt;li&gt;GPU acceleration via CUDA for NVIDIA cards (CPU fallback works without one)&lt;/li&gt;&lt;li&gt;Welcome window on first launch to pick and download a Whisper model&lt;/li&gt;&lt;li&gt;Microphone selector, input gain, and Chromium noise suppression toggle&lt;/li&gt;&lt;li&gt;Pill position grid (corners and center top/bottom), per-display preference, remembers last drag position&lt;/li&gt;&lt;li&gt;Auto-recovery: if the active model is deleted while the app is running, the welcome reopens to redownload&lt;/li&gt;&lt;/ul&gt;</description><pubDate>Sun, 10 May 2026 00:00:00 GMT</pubDate></item></channel></rss>