- Download and configure Kerstin Piper voice (63MB, local)
- Update piper_service.py to support multiple voice models
- Set de_kerstin as default voice for TTS bot
- Update help text with new voice options
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The /synthesize/piper endpoint doesn't exist - use /synthesize/auto
which automatically routes to the correct TTS backend based on voice.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Export the following from @manacore/bot-services:
- LOGIN_MESSAGES: Pre-defined auth error messages for all bot types
- AUTH_ERROR_MESSAGES: Same as LOGIN_MESSAGES (preferred name)
- formatAuthErrorMessage(): Helper to create custom auth error messages
These are used by bots to show consistent error messages when token
refresh fails and the user needs to re-authenticate.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
MP3 format was causing "no supported sources" error in Element.
Switch to WAV which has broader browser/client support.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add TTS_API_KEY config option to configuration.ts
- Send X-API-Key header in TtsService requests
- Update docker-compose.macmini.yml with TTS_INTERNAL_API_KEY env var
- Update .env.example and CLAUDE.md documentation
The mana-tts service requires authentication, but the TTS bot was not
sending the required X-API-Key header, causing 401 errors.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
All 19 Matrix bots now use SessionModule.forRoot({ storageMode: 'redis' })
to share user sessions across all bots via Redis. Users only need to
login once with any bot to be authenticated with all bots.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add loginWithLoginToken function to exchange Matrix SSO loginToken for credentials.
The app layout now detects the loginToken URL parameter and completes the SSO flow.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add TranscriptionModule and handleAudioMessage to enable voice message
transcription across all Matrix bots. Users can now send voice messages
which are automatically transcribed and processed as text commands.
Affected bots:
- matrix-calendar-bot
- matrix-chat-bot
- matrix-contacts-bot
- matrix-manadeck-bot
- matrix-ollama-bot
- matrix-picture-bot
- matrix-planta-bot
- matrix-presi-bot
- matrix-questions-bot
- matrix-skilltree-bot
- matrix-stats-bot
- matrix-storage-bot
- matrix-tts-bot
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- All bots now use HealthController from @manacore/matrix-bot-common
- Deleted 19 duplicate health.controller.ts files
- Added IConfigService interface for @nestjs/config v3/v4 compatibility
- matrix-stats-bot migrated to use BaseMatrixService as example
- All 19 bots pass type-check
This consolidation eliminates ~400 lines of duplicate health check code.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- NestJS bot that converts text messages to speech via mana-tts
- Commands: !voice, !voices, !speed, !status, !help
- User settings stored in-memory (voice, speed per user)
- Docker config for Mac Mini deployment
- Setup script for bot registration
Co-Authored-By: Claude <noreply@anthropic.com>
