VoiceTray lives in your tray. Press a hotkey, speak, and it types into whatever app you’re using. It cleans transcripts conservatively with deterministic rules, then optionally applies an on-device LLM cleanup step with strict safety checks and fallback.
Runs in the system tray. One hotkey to dictate into the active app, another to save notes to files.
Uses faster-whisper locally for dictation without sending audio anywhere. There is no cloud fallback during dictation.
Expand short triggers into full text using snippets.txt after cleanup.
Keep raw and cleaned dictations in local SQLite history for quick capture, search, copy, and re-insert.
Protect names and technical terms, plus apply custom replacements using glossary.json.
Choose cleanup mode (raw/balanced/aggressive), formatting profile (email/chat/notes/code), and per-app overrides.
Accuracy is prioritized over aggressive paraphrasing. If the model output looks unsafe, it is rejected automatically.
VoiceTray is usable offline. Optional local LLM cleanup runs on-device and remains guarded by validation + fallback.