Back to list
WhisperApp v0.10.3
Released: February 25, 2026
New Features
- Speaker diarization engine overhaul — Migrated to sherpa-onnx engine. CUDA / CPU support, per-model optimal thresholds for improved accuracy
- Real-time transcription — High-accuracy real-time transcription powered by Silero VAD. Dual capture (mic + internal audio), per-segment language switching, context carry-over
- App auto-updater — Automatic update notification and installation on new releases
- File association — Double-click audio files to open them directly in WhisperApp
- Speaker count selection — Specify number of speakers for diarization
- Standard / Pro plans — Plan-based feature gating
Improvements
- Real-time transcription settings now persist between sessions
- Elapsed time stopwatch display
- Output format (TXT / SRT / VTT, etc.) settings persistence
- Faster file I/O in the editor
- Engine auto-download settings controllable from installer
- yt-dlp auto-update support
- Real-time transcription pauses when recording is paused
Bug Fixes
- Fixed root cause of Fatal Aborted crashes during processing
- Fixed timestamp drift in real-time transcription
- Fixed race condition when opening multiple files simultaneously
- Uninstaller now removes config, engines, and license files
- Fixed custom speaker names not displaying correctly in audio bars