TypeWhisper 1.4.0-rc2 refreshes the 1.4 release-candidate line on the current main branch. This candidate is based on e9808037 and focuses on workflow ordering, recorder reliability, plugin SDK polish, and integration fixes since 1.4.0-rc1.
Highlights
- Added drag-and-drop ordering for workflows, with matching priority following the saved workflow order.
- Kept workflow reordering disabled while search is filtering the list, so filtered subsets do not rewrite global priority by accident.
- Added combined workflow trigger support and spoken-punctuation compatibility coverage for older workflow behavior.
- Improved recorder reliability for FaceTime/system audio sample handling and selected USB microphones with mismatched output clocks.
- Fixed Gemma plugin cache recovery after failed downloads.
- Added structured speaker diarization support for AssemblyAI through the Plugin SDK path.
- Tightened the 1.4 community plugin registry automation and permissions.
- Replaced spoken-language flag icons with neutral language badges.
- Fixed fixed-display indicators in fullscreen Spaces and clarified the German recorder settings label.
Testing Focus
- Verify workflow drag reorder affects matching priority and remains disabled while filtering.
- Smoke-test combined trigger workflows and spoken-punctuation compatibility controls.
- Record with selected USB microphones and system audio or FaceTime paths.
- Retry a Gemma model download after failure and verify cache recovery.
- Check AssemblyAI diarization settings and structured speaker labels.
- Confirm the 1.4 community registry feed and Integrations tabs still resolve plugins correctly.
- Verify fixed-display indicators in fullscreen Spaces.