tts-voice-creator-clone-and.../architecture
mARTin-B78 37e2622d4e feat(audiobook): advisory verify and span-native recast for span casts
Verify / recast now run span-natively (no text re-emission): a second differently-windowed
pass marks lines agreed/disputed and records the other answer, without changing any speaker
(~9 min vs ~49 min). Measured on the real pipeline, overruling disputed lines with a reasoning
adjudication made them worse (66.5% -> 61.4%), so that step was removed; agreed lines were 83%
right vs 48.5% for disputed ones, which is the signal used for confidence and review.
Auto-repair no longer runs after a span cast; segments carry a spanId.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-09-19 20:17:38 +02:00
..
audiobook-attribution.md feat(audiobook): advisory verify and span-native recast for span casts 2026-09-19 20:17:38 +02:00
character-visual-identity.md fix(characters): persist base-appearance image pairs, deterministic prompts, form-aware review; add forms panel 2026-09-19 15:27:21 +02:00
magazine-ingestion.md fix(magazine): catch vision OCR decoding loops before they become page text 2026-09-13 10:09:32 +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