TypeWhisper 1.4.0-rc3 refreshes the 1.4 release-candidate line from current main (855a5823). This candidate focuses on lower-latency dictation starts, workflow engine overrides, audio diagnostics, model/plugin refreshes, licensed term packs, watch-folder file jobs, and memory extraction fixes since 1.4.0-rc2.
Highlights
- Added the OpenAI voice refresh for TypeWhisper 1.4 and refreshed the Qwen3 ASR plugin for 1.1.0.
- Reduced hotkey recording start latency and cold-start latency.
- Fixed exact modifier-combo hotkey matching.
- Added dictation workflow engine overrides.
- Removed legacy profile runtime rules.
- Added support diagnostics export for audio device failures.
- Allowed USB input selection without preflight capture.
- Added licensed industry term packs.
- Fixed Parakeet startup model selection status.
- Fixed memory extraction for normal dictations.
- Added watch folder file-job automation.
Testing Focus
- Verify hotkey start/cold-start latency and exact modifier combinations.
- Smoke-test dictation workflow engine overrides and normal dictation memory extraction.
- Export audio diagnostics and select USB input devices without preflight capture.
- Check OpenAI, Qwen3, and Parakeet plugin/model settings.
- Download and apply licensed industry term packs.
- Run watch folder file-job automation.
- Confirm the RC release publishes DMG/ZIP assets and updates Sparkle on the
release-candidatechannel.