- Create VoicePreferencesStore for file-based persistence
- Preferences saved to data/voice-preferences.json
- Add autoVoiceReply setting for voice message auto-response
- Add !speed command for speech speed control (0.5-2.0x)
- Add !voice auto an/aus for auto-reply toggle
- Update HELP_TEXT with voice command documentation
- Debounced save with 1s delay for performance
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create VoiceFormatterService for intelligent speech formatting
- Convert numbers to German words (eins, zwei, drei...)
- Convert times to natural speech (10:00 → zehn Uhr, 14:30 → halb drei)
- Convert dates to German format (15.02. → 15. Februar)
- Format task metadata (!p1 → mit höchster Priorität, @heute → fällig heute)
- Summarize long lists (top 3 + "und X weitere")
- Convert numbered lists to ordinals (Erstens, Zweitens, Drittens)
- Smart truncation at sentence boundaries
- Remove inline prepareTextForSpeech(), use formatter service
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add VoiceModule and VoiceService for STT integration
- Override handleAudioMessage to process voice notes
- Transcribe audio via mana-stt (Whisper)
- Route transcribed text through CommandRouter
- Add voice configuration and environment variables
- Update help text and documentation
Voice flow:
1. User sends voice note
2. Bot downloads and transcribes audio
3. Shows transcription: 🎤 *"text"*
4. Routes as normal text command
5. Returns text response
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
