Till JS 8823cc0bf0 feat(profile): voice interview with pre-rendered TTS audio + Orpheus/Zonos backends ...

Voice-based interview for the profile module — users choose between text,
voice (question read aloud + mic for answer), or conversation mode (fully
automatic flow with auto-save).

Interview audio:
- 92 pre-rendered MP3 files (23 questions × 4 voices) via Edge TTS
- Voices: Seraphina (DE-f), Florian (DE-m), Leni (CH-f), Jan (CH-m)
- User picks voice via dropdown, persisted in localStorage
- Web Speech API fallback for missing audio files

Profile UI:
- Interview hero block on overview with 3 start modes (text/voice/conversation)
- Voice/conversation toggle + voice picker in interview view
- Mic button on text/textarea/tags inputs for per-question voice input
- Conversation mode: auto-save + auto-advance after STT transcription
- Recording/transcribing/speaking state indicators

mana-tts service:
- New Orpheus TTS backend (German finetune, SNAC codec)
- New Zonos TTS backend (Zyphra, 200k hours, emotion control)
- Endpoints: POST /synthesize/orpheus, POST /synthesize/zonos
- espeak-ng installed on GPU server for Zonos phonemizer
- Compare script for side-by-side voice quality testing

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-17 15:22:52 +02:00

20 KiB

Raw History

View raw