tts-voice-creator-clone-and.../architecture
mARTin-B78 7eabdf0e43 feat(characters): distinct deterministic face profiles per character
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-03 14:25:56 +02:00
..
evidence feat: OCR benchmark harness and first candidate results (docling, PaddleOCR) 2026-09-29 17:55:48 +02:00
audiobook-attribution.md fix(audiobook): warm the model before span cast/verify; keep tests off the real LLM 2026-09-19 21:08:01 +02:00
character-extraction.md fix(characters): merge profiles only on real names, keep other cast names, reasoning and foreign quotes out of a character 2026-10-03 14:09:53 +02:00
character-visual-identity.md feat(characters): distinct deterministic face profiles per character 2026-10-03 14:25:56 +02:00
magazine-ingestion.md feat(magazine): record/replay cache for vision responses in OCR comparisons 2026-10-03 11:09:17 +02:00
magazine-sources.md feat(magazine): manage OPDS catalogues in the app, env-based login, result paging 2026-09-30 11:03:03 +02:00
multi-tenant-and-identity.md fix(engines): resolve LiteLLM card's own key server-side instead of a stale global one 2026-09-14 13:58:54 +02:00
ocr-porting-prompt-general.md docs: general-purpose OCR porting brief for letters, papers and forms 2026-09-30 10:10:59 +02:00
ocr-porting-prompt.md docs: OCR porting brief; test: current prompt version fixture, known phone-width issue 2026-09-29 21:38:28 +02:00
voicestudio-comparison.md docs: deep-dive UI/UX and feature-parity comparison with VoiceStudio 2026-09-29 13:46:14 +02:00