Benjamin Admin 198a0b2a0d Fix: Use /synthesize-direct for correct language selection ...

/synthesize always used the German model. /synthesize-direct uses
Edge TTS (with language-aware voice selection) and falls back to
Piper with the correct model (Thorsten DE / Lessac EN).

Also cleared audio cache to purge wrongly-generated files.

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

2026-04-26 23:46:40 +02:00

..

__init__.py

Restructure: Move final 16 root files into packages (backend-lehrer)

2026-04-25 22:50:37 +02:00

ai_processor.py

Cleanup: Delete ALL 242 shims, update ALL consumer imports

2026-04-26 00:11:33 +02:00

audio.py

Fix: Use /synthesize-direct for correct language selection

2026-04-26 23:46:40 +02:00

claude_vision.py

Restructure: Move final 16 root files into packages (backend-lehrer)

2026-04-25 22:50:37 +02:00

email.py

Restructure: Move final 16 root files into packages (backend-lehrer)

2026-04-25 22:50:37 +02:00

file_processor_models.py

[split-required] Split final 43 files (500-668 LOC) to complete refactoring

2026-04-25 09:41:42 +02:00

file_processor.py

[split-required] Split final 43 files (500-668 LOC) to complete refactoring

2026-04-25 09:41:42 +02:00

pdf_models.py

[split-required] Split 500-1000 LOC files across all services

2026-04-24 23:35:37 +02:00

pdf_service.py

[split-required] Split 500-1000 LOC files across all services

2026-04-24 23:35:37 +02:00

pdf_templates.py

[split-required] Split 500-1000 LOC files across all services

2026-04-24 23:35:37 +02:00

story_generator.py

Restructure: Move final 16 root files into packages (backend-lehrer)

2026-04-25 22:50:37 +02:00

translation.py

Cleanup: Delete ALL 242 shims, update ALL consumer imports

2026-04-26 00:11:33 +02:00